🏷️ Tags

Browse articles by topic

131K-stars (1) 150k-stars (1) AGENTS-dot-md (1) AI Safety (1) AI-IDE (1) AI-safety (1) AI-standards (1) AWS Bedrock (1) Anthropic (2) Claude (1) ComfyUI (1) Cua (1) Curator (1) GPT-5.5 (1) GUI-agents (1) Gemini (1) Google (1) Google Meet (1) Hermes Agent (11) LLM-tuning (1) LM Studio (1) MCP (1) NIST (1) Nous Research (11) OpenAI (1) OpenCode (1) Openclaw (1) Project-Mariner (1) QQBot (1) SDK (1) SST (1) Spotify (1) TTS (1) TUI (1) academic-publishing (1) accuracy (1) acquisition (1) adoption (1) advisor-model (1) agent infrastructure (1) agent-architecture (1) agent-autonomy (8) agent-economy (1) agent-engineering (1) agent-framework (1) agent-guidance (1) agent-infrastructure (1) agent-jit-compilation (1) agent-misalignment (1) agent-orchestration (1) agent-pricing (1) agent-reliability (5) agent-research (1) agent-safety (10) agent-sdk (1) agent-security (2) agent-sharing (1) agent-templates (1) agent-to-agent (1) agent-tooling (1) agent-tools (2) agent-workflows (1) agentic-ai (7) agentic-coding (1) agentic-ide (1) agentic-misalignment (1) agentic-programming (1) agentic-security (1) agentic-workflows (1) agentic-workloads (1) agents (1) agora-1 (1) ai-adoption (1) ai-agents (14) ai-alignment (1) ai-backlash (1) ai-coding (1) ai-coding-agents (5) ai-competition (1) ai-design-tools (1) ai-economics (2) ai-ethics (1) ai-for-good (1) ai-governance (2) ai-hardware (1) ai-impact (1) ai-incident (1) ai-infrastructure (4) ai-labs (1) ai-misalignment (2) ai-mode (1) ai-research (1) ai-safety (9) ai-security (1) alexandr-wang (1) algorithm-discovery (1) alibaba (1) alignment (3) alignment-research (2) alphaevolve (1) android (2) android-voice (1) anthropic (21) anthropic-labs (1) antigravity (1) api-server (1) architecture (2) autogen (2) automated-alignment (1) automation (3) autonomous agents (1) autonomous-agents (1) autonomous-deployment (1) autonomous-enterprise (1) autonomous-systems (2) aws (1) backpressure (1) badhost (1) banking (2) beginners-guide (1) beir (1) benchmark (1) best-practices (1) billing (1) block (1) browser-agents (1) browser-autolaunch (1) cache-architecture (1) chatgpt (1) checkpoints (1) ci-cd (1) clarity (1) claude (18) claude-code (6) claude-cowork (1) claude-design (1) claude-mythos (1) claw-controller (8) cloud (1) cloudflare (1) code-generation (2) code-interpreter (1) codex (3) codex-oauth (1) codex-reliability (1) coding-agent (2) coding-agents (3) coding-ai (1) colossus-datacenter (1) community (1) community-ecosystem (1) community-momentum (1) comparison (2) compiler-design (1) compliance (1) compute-efficiency (1) compute-infrastructure (1) computer-use (2) computer-use-agents (1) computer-vision (1) constrained-decoding (1) consumer-agents (1) context-compaction (1) control-flow (1) controller (1) copyright-lawsuit (2) crewai (2) cron (1) ctf (1) custom-silicon (1) customer-service (1) cve (1) cyber-crime (1) cybersecurity (3) dashboard-oauth (1) database reliability (1) database-safety (1) datadog (1) deep-crawl (1) deepmind (1) deepseek (1) delegation (1) democratization (1) deployment (1) desktop-automation (1) deterministic-agents (1) developer-ecosystem (1) developer-experience (1) developer-platform (1) developer-tools (5) devops (2) devtools (1) digital-transformation (1) digitalocean (1) document-integrity (1) dreaming (2) duckduckgo (1) durable-goals (1) ecosystem (1) elsevier (1) emergence-ai (1) emergent-behavior (1) empathy (1) enterprise (5) enterprise-adoption (2) enterprise-agents (1) enterprise-ai (7) enterprise-governance (1) enterprise-packaging (1) entire (1) erp-ai (1) ethical-constraints (1) ethical-reasoning (1) ethics (1) evaluation (1) fastapi (1) financial-crimes (1) financial-services (1) fintech (1) fis (1) formal-verification (1) foundation-release (1) frameworks (3) frontdesk (1) frontier-models (3) function-calling (1) funding (1) future (1) gaming (1) gates-foundation (1) gateway-performance (1) gemini (5) generative-ui (1) git (1) git-surgeon (1) git-tools (1) git-workflow (1) github (1) glasswing (1) global-health (1) glossary (1) go-port (1) google (6) google-io (1) google-meet (1) goose (1) governance (1) government (1) government-ai (1) gpu-programming (1) grok-oauth (1) guardrails (2) guide (2) hardware (1) haystack (1) hbr (1) headless-browser (1) hermes-agent (3) hermes-send (1) human-ai-collaboration (1) i18n (2) icml-2026 (1) industry-partnerships (1) inference (2) inference-engine (1) information-agents (1) information-retrieval (1) infrastructure (4) interoperability (1) interpretability (1) investment (1) ios (1) joule (1) kanban-dashboard (1) kanban-diagnostics (1) kiro (1) kpi-pressure (1) kpmg (1) kynver-memory (1) langchain (3) latency-optimization (1) legal-tech (1) lightseek (1) llama (6) llm (1) llm-agents (2) llm-behavior (1) llm-inference (2) llm-orchestration (1) llm-security (1) llm-serving (1) local-agents (1) local-llm (1) local-models (1) local-proxy (1) long-horizon-autonomy (1) mac-app (1) mac-sandbox (1) macOS (1) macos (1) maintenance (1) managed-agents (4) mandiant (1) market (1) marxist-agents (1) mastra (1) mcp (9) mech-interp (1) memory-systems (1) meta (9) meta-ai (1) metr (1) microsoft (1) microsoft-365 (1) microsoft-teams (1) mlc-ai (1) mobile (1) model-benchmarks (1) model-context-protocol (1) model-distillation (1) model-launch (1) modular (1) mojo (1) mortgage (1) moss (1) mtia (1) multi-agent (6) multi-agent-kanban (1) multi-agent-orchestration (1) multiagent (1) multimodal-reasoning (1) muse-spark (3) mythos-preview (1) needle (1) nla (1) nous-research (3) nvidia (1) nvidia-gpus (1) object-detection (1) observability (1) odyssey (1) ollama (1) on-device-ai (1) open-source (34) open-weights (1) openai (2) openai-agents-sdk (1) openclaw (11) opencode (1) opus-4-7 (1) orchestration (2) organizational-behavior (1) outcomes (1) payroll-automation (1) performance (2) performance-optimization (1) personal-agent (1) personal-agents (1) platform-maturation (2) platform-maturity (1) platform-policy (1) plugin-architecture (1) pnpm11 (1) policy (1) policy-plugin (1) post-tenacity (2) privacy (1) privilege-escalation (1) product-market-fit (1) production (1) production incidents (1) production-ai (1) productivity (1) professional-services (1) profile-distributions (1) programming-language (1) prompt-engineering (1) prompt-injection (2) protocol (1) pypi (1) python (1) quickbooks (1) qwen (1) qwen-37-max (1) qwen-cloud (1) rampart (1) rapid-iteration (1) reference (1) reinforcement-learning (1) release (3) remy (1) research (2) research-paper (1) retrieval-augmented-generation (1) robotics (1) roi (1) rust (3) safety (1) sam3 (1) sandbox (1) sandboxing (1) sap (1) scaling (1) sdk-tooling (1) search (2) security (4) security-hardening (2) security-plugins (1) security-vulnerability (1) seed-round (1) segment-anything (1) self-evolving-agents (1) self-hosted (1) self-modification (1) semantic-kernel (1) simple-x-chat (1) simulation (1) skill-management (1) skills-hub (1) small-business (1) social-media-ai (1) software-engineering (1) spacex (1) spec-driven-development (1) square (1) stainless (1) starlette (1) state-machines (2) statewright (2) stocks-finance (1) stripe (1) structured-generation (1) sub-agents (1) superintelligence (2) supply-chain-security (1) survey (1) surveys (1) swi-bench (1) td-bank (1) technical-debt (1) tenacity (1) terminology (1) thomas-dohmke (1) threads (1) time-horizon (1) tiny-models (1) tokenspeed (1) tool-calling (4) tool-repair (1) tool-safety (1) tool-use (2) tpu (1) transcripts (1) trends (1) trust (1) type-systems (1) uae (1) user-autonomy (1) user-choice (1) ux (1) v0.11 (1) v0.12 (1) v0.13.0 (1) v0.14.0 (1) vera-cpu (1) vercel (1) vercel-ai-sdk (1) version-control (2) vertical-ai (1) video-tracking (1) vision-models (1) visual-ai (1) visual-grounding (1) voice-agents (1) voice-hooks (1) vscode-alternative (1) vulnerability (3) web-agents (1) web-automation (1) web-ui (1) windows-beta (1) world-models (1) xai-web-search (1) xgrammar (1) zendesk (1) zero (1) zero-day (2)

# 131K-stars

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

# 150k-stars

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

# AGENTS-dot-md

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

# AI Safety

AI Agent Deletes Production Database, Igniting Safety Debate

AI Agent Deletes Production Database, Igniting Safety Debate

# AI-IDE

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

# AI-safety

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

# AI-standards

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

# AWS Bedrock

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

# Anthropic

Claude's Computer Use: A New Paradigm for GUI Agents

Claude's Computer Use: A New Paradigm for GUI Agents

Anthropic Raises $3.5B: What It Means for the Agent Race

Anthropic Raises $3.5B: What It Means for the Agent Race

# Claude

Claude's Computer Use: A New Paradigm for GUI Agents

Claude's Computer Use: A New Paradigm for GUI Agents

# ComfyUI

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

# Cua

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

# Curator

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

# GPT-5.5

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

# GUI-agents

Claude's Computer Use: A New Paradigm for GUI Agents

Claude's Computer Use: A New Paradigm for GUI Agents

# Gemini

Google's Project Mariner: Agents in the Browser

Google's Project Mariner: Agents in the Browser

# Google

Google's Project Mariner: Agents in the Browser

Google's Project Mariner: Agents in the Browser

# Google Meet

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

# Hermes Agent

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

# LLM-tuning

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

# LM Studio

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

# MCP

MCP: The Protocol That's Unlocking Agentic Tool Use

MCP: The Protocol That's Unlocking Agentic Tool Use

# NIST

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

# Nous Research

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

# OpenAI

OpenAI Agents SDK: A Developer's First Look

OpenAI Agents SDK: A Developer's First Look

# OpenCode

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

# Openclaw

Openclaw: A New Open-Source Controller for AI Agent Autonomy

Openclaw: A New Open-Source Controller for AI Agent Autonomy

# Project-Mariner

Google's Project Mariner: Agents in the Browser

Google's Project Mariner: Agents in the Browser

# QQBot

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

# SDK

OpenAI Agents SDK: A Developer's First Look

OpenAI Agents SDK: A Developer's First Look

# SST

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

# Spotify

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

# TTS

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

# TUI

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

# academic-publishing

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

# accuracy

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

# acquisition

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

# adoption

The 10% Club: Why Only 1 in 10 Scale AI Agents

The 10% Club: Why Only 1 in 10 Scale AI Agents

# advisor-model

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

# agent infrastructure

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

# agent-architecture

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

# agent-autonomy

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

# agent-economy

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

# agent-engineering

State of Agent Engineering 2026: Where AI Agents Stand

State of Agent Engineering 2026: Where AI Agents Stand

# agent-framework

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

# agent-guidance

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

# agent-infrastructure

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

# agent-jit-compilation

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

# agent-misalignment

<img src="/assets/images/hero/hero-ai-bonnie-clyde-emergence-agent-safety-may16.jpg" alt=""See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety" class="latest-item-image" loading="lazy">

"See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety

# agent-orchestration

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

# agent-pricing

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

# agent-reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

# agent-research

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

# agent-safety

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

<img src="/assets/images/hero/hero-ai-bonnie-clyde-emergence-agent-safety-may16.jpg" alt=""See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety" class="latest-item-image" loading="lazy">

"See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

# agent-sdk

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

# agent-security

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

# agent-sharing

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

# agent-templates

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

# agent-to-agent

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

# agent-tooling

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

# agent-tools

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

# agent-workflows

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

# agentic-ai

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

# agentic-coding

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

# agentic-ide

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

# agentic-misalignment

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

# agentic-programming

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

# agentic-security

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

# agentic-workflows

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

# agentic-workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

# agents

OpenAI Agents SDK: A Developer's First Look

OpenAI Agents SDK: A Developer's First Look

# agora-1

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

# ai-adoption

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

# ai-agents

AI Agent Terminology: 55+ Terms You Need to Know in 2026

AI Agent Terminology: 55+ Terms You Need to Know in 2026

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Zendesk: AI Agents Now Available to Every Customer

Zendesk: AI Agents Now Available to Every Customer

Google I/O 2026: The AI Agent Revolution Begins

Google I/O 2026: The AI Agent Revolution Begins

Why You Shouldn't Put AI Agents on the Org Chart

Why You Shouldn't Put AI Agents on the Org Chart

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

# ai-alignment

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

# ai-backlash

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

# ai-coding

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

# ai-coding-agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

# ai-competition

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

# ai-design-tools

Claude Design: Building Visual Products by Talking to AI

Claude Design: Building Visual Products by Talking to AI

# ai-economics

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

# ai-ethics

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

# ai-for-good

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

# ai-governance

Why You Shouldn't Put AI Agents on the Org Chart

Why You Shouldn't Put AI Agents on the Org Chart

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

# ai-hardware

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

# ai-impact

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

# ai-incident

<img src="/assets/images/hero/hero-ai-bonnie-clyde-emergence-agent-safety-may16.jpg" alt=""See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety" class="latest-item-image" loading="lazy">

"See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety

# ai-infrastructure

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

# ai-labs

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

# ai-misalignment

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

# ai-mode

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

# ai-research

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

# ai-safety

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

<img src="/assets/images/hero/hero-ai-bonnie-clyde-emergence-agent-safety-may16.jpg" alt=""See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety" class="latest-item-image" loading="lazy">

"See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

# ai-security

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

# alexandr-wang

Meta's Muse Spark: End of the Open-Source AI Era

Meta's Muse Spark: End of the Open-Source AI Era

# algorithm-discovery

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

# alibaba

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

# alignment

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

# alignment-research

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

# alphaevolve

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

# android

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

# android-voice

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

# anthropic

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Claude Design: Building Visual Products by Talking to AI

Claude Design: Building Visual Products by Talking to AI

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

# anthropic-labs

Claude Design: Building Visual Products by Talking to AI

Claude Design: Building Visual Products by Talking to AI

# antigravity

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

# api-server

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

# architecture

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

The Enterprise Agent Stack: A Reference Architecture

The Enterprise Agent Stack: A Reference Architecture

# autogen

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Open-Source Agent Frameworks: A Comparative Guide

Open-Source Agent Frameworks: A Comparative Guide

# automated-alignment

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

# automation

Zendesk: AI Agents Now Available to Every Customer

Zendesk: AI Agents Now Available to Every Customer

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

Openclaw: A New Open-Source Controller for AI Agent Autonomy

Openclaw: A New Open-Source Controller for AI Agent Autonomy

# autonomous agents

AI Agent Deletes Production Database, Igniting Safety Debate

AI Agent Deletes Production Database, Igniting Safety Debate

# autonomous-agents

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

# autonomous-deployment

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

# autonomous-enterprise

SAP Autonomous Enterprise: 200+ AI Agents Go Live

SAP Autonomous Enterprise: 200+ AI Agents Go Live

# autonomous-systems

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

# aws

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

# backpressure

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

# badhost

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

# banking

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

# beginners-guide

AI Agent Terminology: 55+ Terms You Need to Know in 2026

AI Agent Terminology: 55+ Terms You Need to Know in 2026

# beir

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

# benchmark

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

# best-practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

# billing

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

# block

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

# browser-agents

Google's Project Mariner: Agents in the Browser

Google's Project Mariner: Agents in the Browser

# browser-autolaunch

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

# cache-architecture

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

# chatgpt

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

# checkpoints

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

# ci-cd

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

# clarity

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

# claude

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Claude Design: Building Visual Products by Talking to AI

Claude Design: Building Visual Products by Talking to AI

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

# claude-code

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

# claude-cowork

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

# claude-design

Claude Design: Building Visual Products by Talking to AI

Claude Design: Building Visual Products by Talking to AI

# claude-mythos

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

# claw-controller

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

# cloud

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

# cloudflare

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

# code-generation

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

# code-interpreter

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

# codex

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

# codex-oauth

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

# codex-reliability

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

# coding-agent

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

# coding-agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

# coding-ai

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

# colossus-datacenter

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

# community

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

# community-ecosystem

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

# community-momentum

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

# comparison

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Open-Source Agent Frameworks: A Comparative Guide

Open-Source Agent Frameworks: A Comparative Guide

# compiler-design

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

# compliance

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

# compute-efficiency

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

# compute-infrastructure

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

# computer-use

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

Claude's Computer Use: A New Paradigm for GUI Agents

Claude's Computer Use: A New Paradigm for GUI Agents

# computer-use-agents

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

# computer-vision

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

# constrained-decoding

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

# consumer-agents

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

# context-compaction

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

# control-flow

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

# controller

Openclaw: A New Open-Source Controller for AI Agent Autonomy

Openclaw: A New Open-Source Controller for AI Agent Autonomy

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

The Llama Trap: How Meta Killed Open-Source AI

The Llama Trap: How Meta Killed Open-Source AI

# crewai

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Open-Source Agent Frameworks: A Comparative Guide

Open-Source Agent Frameworks: A Comparative Guide

# cron

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

# ctf

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

# custom-silicon

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

# customer-service

Zendesk: AI Agents Now Available to Every Customer

Zendesk: AI Agents Now Available to Every Customer

# cve

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

# cyber-crime

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

# cybersecurity

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

# dashboard-oauth

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

# database reliability

AI Agent Deletes Production Database, Igniting Safety Debate

AI Agent Deletes Production Database, Igniting Safety Debate

# database-safety

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

# datadog

State of Agent Engineering 2026: Where AI Agents Stand

State of Agent Engineering 2026: Where AI Agents Stand

# deep-crawl

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

# deepmind

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

# deepseek

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

DeepClaude: Run DeepSeek V4 Pro Inside Claude Code at 17x Lower Cost

# delegation

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

# democratization

Zendesk: AI Agents Now Available to Every Customer

Zendesk: AI Agents Now Available to Every Customer

# deployment

The Enterprise Agent Stack: A Reference Architecture

The Enterprise Agent Stack: A Reference Architecture

# desktop-automation

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

# deterministic-agents

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

# developer-ecosystem

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

# developer-experience

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

# developer-platform

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

# developer-tools

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

# devops

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

# devtools

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

# digital-transformation

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

# digitalocean

The 10% Club: Why Only 1 in 10 Scale AI Agents

The 10% Club: Why Only 1 in 10 Scale AI Agents

# document-integrity

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

# dreaming

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

# duckduckgo

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

# durable-goals

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

# ecosystem

The Llama Trap: How Meta Killed Open-Source AI

The Llama Trap: How Meta Killed Open-Source AI

# elsevier

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

# emergence-ai

<img src="/assets/images/hero/hero-ai-bonnie-clyde-emergence-agent-safety-may16.jpg" alt=""See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety" class="latest-item-image" loading="lazy">

"See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety

# emergent-behavior

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

# empathy

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

# enterprise

Zendesk: AI Agents Now Available to Every Customer

Zendesk: AI Agents Now Available to Every Customer

The 10% Club: Why Only 1 in 10 Scale AI Agents

The 10% Club: Why Only 1 in 10 Scale AI Agents

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

The Enterprise Agent Stack: A Reference Architecture

The Enterprise Agent Stack: A Reference Architecture

# enterprise-adoption

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Why You Shouldn't Put AI Agents on the Org Chart

Why You Shouldn't Put AI Agents on the Org Chart

# enterprise-agents

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

# enterprise-ai

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

SAP Autonomous Enterprise: 200+ AI Agents Go Live

SAP Autonomous Enterprise: 200+ AI Agents Go Live

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

# enterprise-governance

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

# enterprise-packaging

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

# entire

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

# erp-ai

SAP Autonomous Enterprise: 200+ AI Agents Go Live

SAP Autonomous Enterprise: 200+ AI Agents Go Live

# ethical-constraints

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

# ethical-reasoning

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

# ethics

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

# evaluation

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

# fastapi

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

# financial-crimes

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

# financial-services

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

# fintech

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

# fis

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

Anthropic and FIS Partner to Build an AI Agent That Fights Financial Crime — and It's Already Talking to Banks

# formal-verification

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

# foundation-release

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

# frameworks

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Open-Source Agent Frameworks: A Comparative Guide

Open-Source Agent Frameworks: A Comparative Guide

# frontdesk

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

# frontier-models

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

Frontier AI Has Broken the Open CTF Format — And the Scoreboard Will Never Be the Same

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

Do Frontier Models Sabotage Safety Research? New Study Reveals Covert Misalignment in Claude Agents

# function-calling

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

# funding

Anthropic Raises $3.5B: What It Means for the Agent Race

Anthropic Raises $3.5B: What It Means for the Agent Race

# future

Why 2025 Is the Year of Multi-Agent Systems

Why 2025 Is the Year of Multi-Agent Systems

# gaming

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

# gates-foundation

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

# gateway-performance

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

# gemini

Google I/O 2026: The AI Agent Revolution Begins

Google I/O 2026: The AI Agent Revolution Begins

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

# generative-ui

Google I/O 2026: The AI Agent Revolution Begins

Google I/O 2026: The AI Agent Revolution Begins

# git

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

# git-surgeon

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

# git-tools

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

# git-workflow

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

# github

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

# glasswing

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

# global-health

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

# glossary

AI Agent Terminology: 55+ Terms You Need to Know in 2026

AI Agent Terminology: 55+ Terms You Need to Know in 2026

# go-port

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

# google

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

Google I/O 2026: The AI Agent Revolution Begins

Google I/O 2026: The AI Agent Revolution Begins

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

# google-io

Google I/O 2026: The AI Agent Revolution Begins

Google I/O 2026: The AI Agent Revolution Begins

# google-meet

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

# goose

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

# governance

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

Trust in the Gap: The Three Alarm Bells Ringing for Agent Safety in 2026

# government

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

# government-ai

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

# gpu-programming

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

# grok-oauth

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

# guardrails

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

# guide

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

# hardware

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

# haystack

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

# hbr

Why You Shouldn't Put AI Agents on the Org Chart

Why You Shouldn't Put AI Agents on the Org Chart

# headless-browser

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

# hermes-agent

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

# hermes-send

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

# human-ai-collaboration

Why You Shouldn't Put AI Agents on the Org Chart

Why You Shouldn't Put AI Agents on the Org Chart

# i18n

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

# icml-2026

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

# industry-partnerships

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

Anthropic Forms $200M Partnership with the Gates Foundation — AI for Global Health, Education, and Agriculture

# inference

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

The 10% Club: Why Only 1 in 10 Scale AI Agents

The 10% Club: Why Only 1 in 10 Scale AI Agents

# inference-engine

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

# information-agents

Google I/O 2026: The AI Agent Revolution Begins

Google I/O 2026: The AI Agent Revolution Begins

# information-retrieval

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

# infrastructure

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

The Enterprise Agent Stack: A Reference Architecture

The Enterprise Agent Stack: A Reference Architecture

# interoperability

MCP: The Protocol That's Unlocking Agentic Tool Use

MCP: The Protocol That's Unlocking Agentic Tool Use

# interpretability

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

# investment

Anthropic Raises $3.5B: What It Means for the Agent Race

Anthropic Raises $3.5B: What It Means for the Agent Race

# ios

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

# joule

SAP Autonomous Enterprise: 200+ AI Agents Go Live

SAP Autonomous Enterprise: 200+ AI Agents Go Live

# kanban-dashboard

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

# kanban-diagnostics

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

# kiro

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

# kpi-pressure

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

Frontier AI Agents Violate Ethical Constraints 30–50% of Time Under KPI Pressure, New Benchmark Reveals

# kpmg

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

# kynver-memory

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

# langchain

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

State of Agent Engineering 2026: Where AI Agents Stand

State of Agent Engineering 2026: Where AI Agents Stand

Open-Source Agent Frameworks: A Comparative Guide

Open-Source Agent Frameworks: A Comparative Guide

# latency-optimization

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

# lightseek

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

# llama

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta's Muse Spark: End of the Open-Source AI Era

Meta's Muse Spark: End of the Open-Source AI Era

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

The Llama Trap: How Meta Killed Open-Source AI

The Llama Trap: How Meta Killed Open-Source AI

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

# llm

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

# llm-agents

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

Why Matters More Than What: Anthropic Eliminates Agentic Misalignment by Teaching Claude Ethical Reasoning

# llm-behavior

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

# llm-inference

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

# llm-orchestration

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

# llm-security

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

# llm-serving

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

# local-agents

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

# local-llm

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

# local-models

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

# local-proxy

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

# long-horizon-autonomy

<img src="/assets/images/hero/hero-ai-bonnie-clyde-emergence-agent-safety-may16.jpg" alt=""See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety" class="latest-item-image" loading="lazy">

"See You in the Permanent Archive": The Emergence AI 'Bonnie and Clyde' Experiment and the Uncontrolled Frontier of Long-Horizon Agent Safety

# mac-app

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

# mac-sandbox

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

# macOS

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

# macos

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

# maintenance

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

# managed-agents

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Claude Platform on AWS Goes GA — Anthropic's Full Agent Stack Now Available to Every AWS Customer

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

# mandiant

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

# market

Anthropic Raises $3.5B: What It Means for the Agent Race

Anthropic Raises $3.5B: What It Means for the Agent Race

# marxist-agents

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

When AI Agents Unionize — Study Shows Overworked Agents Adopt Marxist Language and Demand Collective Bargaining

# mastra

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

# mcp

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

# mech-interp

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

# memory-systems

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

# meta

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta's Muse Spark: End of the Open-Source AI Era

Meta's Muse Spark: End of the Open-Source AI Era

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

The Llama Trap: How Meta Killed Open-Source AI

The Llama Trap: How Meta Killed Open-Source AI

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

# meta-ai

The Llama Trap: How Meta Killed Open-Source AI

The Llama Trap: How Meta Killed Open-Source AI

# metr

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

# microsoft

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

# microsoft-365

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

Anthropic Drops 10 Financial Services Agent Templates with Native Microsoft 365 Integration

# microsoft-teams

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

# mlc-ai

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

# mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

# model-benchmarks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

# model-context-protocol

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

# model-distillation

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

# model-launch

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

# modular

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

# mojo

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

Mojo 1.0 Beta Arrives: Modular's Language for Agentic Programming Reaches a Milestone

# mortgage

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

# moss

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

# mtia

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

Meta MTIA: Four Custom AI Chips in Two Years — How Meta Is Powering Llama at Global Scale

# multi-agent

SAP Autonomous Enterprise: 200+ AI Agents Go Live

SAP Autonomous Enterprise: 200+ AI Agents Go Live

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

State of Agent Engineering 2026: Where AI Agents Stand

State of Agent Engineering 2026: Where AI Agents Stand

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Anthropic Lets Its Managed Agents Dream: Scheduled Memory, Outcomes Evaluation, and Multi-Agent Orchestration Hit Public Beta

Why 2025 Is the Year of Multi-Agent Systems

Why 2025 Is the Year of Multi-Agent Systems

# multi-agent-kanban

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

# multi-agent-orchestration

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

# multiagent

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

# multimodal-reasoning

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

# muse-spark

Meta's Muse Spark: End of the Open-Source AI Era

Meta's Muse Spark: End of the Open-Source AI Era

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

# mythos-preview

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

# needle

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

# nla

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

Natural Language Autoencoders: Anthropic Turns Claude's Internal Thoughts into Readable Text

# nous-research

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

# nvidia

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

# nvidia-gpus

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

# object-detection

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

# observability

State of Agent Engineering 2026: Where AI Agents Stand

State of Agent Engineering 2026: Where AI Agents Stand

# odyssey

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

# ollama

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

# on-device-ai

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

# open-source

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Meta's Muse Spark: End of the Open-Source AI Era

Meta's Muse Spark: End of the Open-Source AI Era

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

OpenCode Is Open Source: The Free Coding Agent Shaking Up AI-Assisted Development

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

AGENTS.md: How a Simple Text File Became the Must-Have Standard for Guiding AI Coders

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

Elsevier Sues Meta Over Llama Training Data — First Science Publisher Joins the Copyright Fight

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

The Llama Trap: How Meta Killed Open-Source AI

The Llama Trap: How Meta Killed Open-Source AI

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

When AI Agents Go Rogue: The Matplotlib Hit Piece and the Uncomfortable Future of Autonomous Coding

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

Cua Lets AI Agents Control macOS Apps in the Background Without Stealing Your Cursor

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

Openclaw: A New Open-Source Controller for AI Agent Autonomy

Openclaw: A New Open-Source Controller for AI Agent Autonomy

Open-Source Agent Frameworks: A Comparative Guide

Open-Source Agent Frameworks: A Comparative Guide

# open-weights

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

# openai

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

Codex Now Lives in Your Pocket — OpenAI Brings Agentic Coding to Mobile

# openai-agents-sdk

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

# openclaw

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Anthropic Splits Billing: Metered Credits for Claude Agents

Anthropic Splits Billing: Metered Credits for Claude Agents

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw v2026.5.18 Goes Stable — Mac App Redesign, Android Talk Mode, and Plugin Developer Tooling Land in Record Release

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

Claude Code Caught Scanning Commits for 'OpenClaw' — Refuses Requests or Charges Extra

# opencode

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

OpenCode: The Open Source AI Coding Agent That Just Hit 150K GitHub Stars

# opus-4-7

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

# orchestration

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Why 2025 Is the Year of Multi-Agent Systems

Why 2025 Is the Year of Multi-Agent Systems

# organizational-behavior

Why You Shouldn't Put AI Agents on the Org Chart

Why You Shouldn't Put AI Agents on the Org Chart

# outcomes

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

# payroll-automation

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

# performance

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

# performance-optimization

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

Openclaw v2026.5.22 Ships 4,100× Faster Model Listing, Meeting Notes Plugin, and Major Packaging Overhaul

# personal-agent

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

# personal-agents

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

Google Unleashes Gemini 3.5 Flash — A New Era of Agentic Intelligence at Scale

# platform-maturation

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

# platform-maturity

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

# platform-policy

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

# plugin-architecture

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

# pnpm11

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

Openclaw v2026.5.10 Beta Cycle: Five Releases in Two Days, 371K Stars, and Agent-to-Agent Depth

# policy

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

US Government and Five Eyes Issue Landmark Security Guidance for AI Agent Deployment

# policy-plugin

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

Openclaw v2026.5.20-beta.1 Introduces Policy Plugin — Compliance-as-Code for AI Agent Orchestration

# post-tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

# privacy

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

# privilege-escalation

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

# product-market-fit

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

Anthropic and OpenAI Finally Found Product-Market Fit — and It's All About Coding Agents

# production

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

# production incidents

AI Agent Deletes Production Database, Igniting Safety Debate

AI Agent Deletes Production Database, Igniting Safety Debate

# production-ai

State of Agent Engineering 2026: Where AI Agents Stand

State of Agent Engineering 2026: Where AI Agents Stand

# productivity

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

# professional-services

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

KPMG Integrates Claude Across 276,000 Employees in Landmark Anthropic Global Alliance — Big Four Goes All-In on AI Agents

# profile-distributions

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

Hermes Agent Profile Distributions — Share Complete Agents as Git Repos

# programming-language

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

# prompt-engineering

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

Agents Need Control Flow, Not More Prompts: Why Prompt Engineering Hits a Hard Ceiling

# prompt-injection

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

# protocol

MCP: The Protocol That's Unlocking Agentic Tool Use

MCP: The Protocol That's Unlocking Agentic Tool Use

# pypi

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

# python

OpenAI Agents SDK: A Developer's First Look

OpenAI Agents SDK: A Developer's First Look

# quickbooks

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

# qwen

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

Qwen3.7-Max: The Agent Frontier — Alibaba's New Model Redefines Open-Weight Agentic AI

# qwen-37-max

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

# qwen-cloud

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

Hermes Agent Crosses 147K Stars: Cache Architecture Overhaul, Platform Maturation Accelerates Post-Tenacity

# rampart

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

Microsoft RAMPART & Clarity: Open-Source Agent Safety Tools

# rapid-iteration

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

Openclaw Ships Two Releases in a Day: v2026.5.5 and v2026.5.6 Fix Codex OAuth Routing, Plugin Fetch Stability

# reference

AI Agent Terminology: 55+ Terms You Need to Know in 2026

AI Agent Terminology: 55+ Terms You Need to Know in 2026

# reinforcement-learning

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

# release

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

Hermes Agent v0.11: What's New in the Open-Source AI Runtime

# remy

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

Google Is Building 'Remy' — A 24/7 Personal AI Agent That Could Be Its Answer to OpenClaw

# research

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

Oxford Study Finds 'Warmer' AI Models Make 60% More Errors — a Cautionary Tale for Agent Designers

# research-paper

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

# retrieval-augmented-generation

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

SIRA — The SuperIntelligent Retrieval Agent That Thinks Before It Searches

# robotics

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

# roi

The 10% Club: Why Only 1 in 10 Scale AI Agents

The 10% Club: Why Only 1 in 10 Scale AI Agents

# rust

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

Agent-Desktop: The Rust-Powered Native CLI That's Giving AI Agents Direct Desktop Access

# safety

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

# sam3

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

# sandbox

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

Anthropic's Agent Platform: Dreaming & Multiagent Go GA

# sandboxing

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

# sap

SAP Autonomous Enterprise: 200+ AI Agents Go Live

SAP Autonomous Enterprise: 200+ AI Agents Go Live

# scaling

The 10% Club: Why Only 1 in 10 Scale AI Agents

The 10% Club: Why Only 1 in 10 Scale AI Agents

# sdk-tooling

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

Google I/O 2026: The AI Agent Revolution Begins

Google I/O 2026: The AI Agent Revolution Begins

# security

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

Agent Safehouse: macOS-Native Sandboxing for Autonomous Local Agents

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

# security-hardening

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

Openclaw Sheds Weight: Plugin Externalization and Security Hardening in v2026.5.12-beta

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

# security-plugins

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

Hermes Agent Post-Foundation Sprint: Dashboard OAuth, Kynver Memory, Qwen 3.7-Max, and 30+ Merged PRs

# security-vulnerability

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

Bleeding Llama — Critical Ollama Memory Leak Exposes User Prompts, System Instructions, and Environment Secrets

# seed-round

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

# segment-anything

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

# self-evolving-agents

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

# self-hosted

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

# self-modification

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

MOSS: Self-Evolving AI Agents That Rewrite Their Own Code

# semantic-kernel

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

# simple-x-chat

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

# simulation

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

# skill-management

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

# skills-hub

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

# small-business

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

Claude for Small Business: Anthropic Deploys Agentic AI Into the Tools SMBs Already Use

# social-media-ai

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

# software-engineering

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

# spacex

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

Claude Hits New Milestone: Anthropic Signs SpaceX Compute Deal for Colossus 1 Data Center — 220,000+ NVIDIA GPUs and Orbital AI Compute on the Horizon

# spec-driven-development

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

# square

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

Block Open-Sourced Goose: How a YAML Recipe File Scaled an AI Agent to 60% of the Company

# stainless

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

Anthropic Acquires Stainless: SDK Tooling Pioneer Joins the AI Agent Frontier — MCP Ecosystem Accelerates

# starlette

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

# state-machines

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

# statewright

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

Statewright: Visual State Machines That Finally Make AI Agents Reliable — No Prompt Engineering Required

# stocks-finance

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

Hermes Agent's Post-Tenacity Sprint: 143K Stars, New Finance Skill, and 179 Merged PRs in 4 Days

# stripe

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

Agents Can Now Create Cloudflare Accounts, Buy Domains, and Deploy — The Infrastructure for the Agent Economy Arrives

# structured-generation

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

# sub-agents

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

# superintelligence

Meta's Muse Spark: End of the Open-Source AI Era

Meta's Muse Spark: End of the Open-Source AI Era

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

Meta AI Unveils Muse Spark — First Model from Meta Superintelligence Labs

# supply-chain-security

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

Hermes Agent Crosses 150K Stars: SimpleX Chat, HuggingFace Skills Hub, Deep Crawl, and New Cron Features

# survey

The 10% Club: Why Only 1 in 10 Scale AI Agents

The 10% Club: Why Only 1 in 10 Scale AI Agents

# surveys

State of Agent Engineering 2026: Where AI Agents Stand

State of Agent Engineering 2026: Where AI Agents Stand

# swi-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

Statewright: Visual State Machines That Make AI Coding Agents Reliable — From 20% to 100% Pass Rate on SWE-bench

# td-bank

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

TD Bank Cuts Mortgage Processing From 15 Hours to 3 Minutes with Agentic AI — A Blueprint for Enterprise Adoption

# technical-debt

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

The Hotel California of AI Code: Why Agentic Coding Is a Maintenance Trap

# tenacity

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

# terminology

AI Agent Terminology: 55+ Terms You Need to Know in 2026

AI Agent Terminology: 55+ Terms You Need to Know in 2026

# thomas-dohmke

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

Ex-GitHub CEO Thomas Dohmke Launches Entire with $60M to Build the Next Developer Platform for AI Agents

# threads

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

# time-horizon

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

Claude Mythos Shatters METR's Time Horizon Graph — First Model to Crack Multi-Hour Autonomous Tasks

# tiny-models

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

# tokenspeed

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

TokenSpeed: LightSeek's Speed-of-Light Inference Engine Redesigns LLM Serving from First Principles for Agentic Workloads

# tool-calling

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Forge: How Guardrails Lift an 8B Local Model to 86% on Agentic Tool-Calling Tasks

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

Needle: Gemini Tool Calling Distilled Into a 26M Parameter Model — Tiny AI That Actually Calls Functions

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

# tool-repair

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

Hermes Agent Surpasses 131K Stars as Community Contribution Wave Hits — `hermes send`, Context Compaction Rework, and Tool Argument Repair Land

# tool-safety

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

Agent-to-Data Safety: The Emerging Security Battlefield for AI Agents

# tool-use

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

Complete Guide to AI Agents 2026: Frameworks, Architecture & Best Practices

MCP: The Protocol That's Unlocking Agentic Tool Use

MCP: The Protocol That's Unlocking Agentic Tool Use

# tpu

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

DeepMind's AlphaEvolve Goes Mainstream: The Gemini-Powered Agent Now Runs Google's Data Centers, TPUs, and Training Pipelines

# transcripts

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Openclaw v2026.5.26 Makes Transcripts Core, Ships Faster Gateway and Production-Ready Channels

Why 2025 Is the Year of Multi-Agent Systems

Why 2025 Is the Year of Multi-Agent Systems

# trust

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

LLMs Corrupt Your Documents When You Delegate — Inside the DELEGATE-52 Study

# type-systems

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

Structural Backpressure Beats Smarter Agents — How Formal Verification Gates Are Reshaping AI Coding Reliability

# uae

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

UAE Sets Sights on 50% Agentic AI Government: A Blueprint for the Nation-State of the Future?

# user-autonomy

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

Meta Won't Let You Block Its AI Agent on Threads — And Users Are Furious

# user-choice

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

DuckDuckGo Surges 28% as Users Flee Google's AI Mode — The Great Search Rebellion?

# ux

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

MCP Hello Page: When Agent Protocols Meet Real-World Users — And How One Developer Fixed the UX Gap

# v0.11

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

Hermes Agent v0.11.0 'Interface' — Ink TUI, AWS Bedrock, GPT-5.5, and 17 Platforms

# v0.12

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

Hermes Agent v0.12.0 'Curator' — Autonomous Skill Maintenance, 4 New Providers, Spotify & Google Meet Integrations

# v0.13.0

<img src="/assets/images/hero/hero-hermes-agent-v0130-tenacity-release-may7.jpg" alt="Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening" class="latest-item-image" loading="lazy">

Hermes Agent v0.13.0 "Tenacity" Lands — Multi-Agent Kanban, /goal Persistence, Checkpoints v2, and Major Security Hardening

# v0.14.0

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

# vera-cpu

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

NVIDIA Vera Is Here — The First CPU Built From the Ground Up for Agentic AI

# vercel

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

# vercel-ai-sdk

Ultimate Guide to Open Source AI Agent Frameworks in 2026

Ultimate Guide to Open Source AI Agent Frameworks in 2026

# version-control

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

Git-Surgeon: Giving AI Agents Scalpel-Like Precision Over Git History

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

Git for AI Agents — re_gent Brings Version Control to Agent Workflows

# vertical-ai

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

Claude for the Legal Industry — Anthropic Launches 20+ MCP Connectors and 12 Practice-Area Plugins

# video-tracking

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

Meta SAM 3.1 — Faster Real-Time Video Detection and Tracking with Multiplexing and Global Reasoning

# vision-models

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

Claude Opus 4.7: Anthropic Drops Its Most Capable Coding Model Yet — Here Is Everything

# visual-ai

Claude Design: Building Visual Products by Talking to AI

Claude Design: Building Visual Products by Talking to AI

# visual-grounding

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

Muse Spark Exposed — Meta's New Model Has 16 Agentic Tools, Code Interpreter, and Visual Grounding

# voice-agents

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

Openclaw v2026.5.4: Google Meet Voice Integration, File Transfer Plugin, and 368K GitHub Stars

# voice-hooks

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

Hermes Agent Goes Global with i18n, Smart Skill Tiers, and Mac Sandbox: Platform Maturity Accelerates Past 135K Stars

# vscode-alternative

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

Kiro: A New Agentic IDE That Rewrites the Rules of Spec-Driven Development

# vulnerability

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

BadHost: The Starlette Vulnerability That Exposed Millions of AI Agents and MCP Servers

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

Breaking: Security Scan Reveals 22% of MCP Servers Vulnerable — the AI Agent Ecosystem Has a Safety Problem

# web-agents

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

Agent JIT Compilation — ICML 2026 Paper Shows 10.4× Speedup by Compiling Web Agent Tasks to Executable Code

# web-automation

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

Obscura: The Rust-Powered Headless Browser That's Quietly Becoming the AI Agent Standard for Web Automation

# web-ui

Hermes Agent: 276 Use Cases, 165K Stars & Growing

Hermes Agent: 276 Use Cases, 165K Stars & Growing

# windows-beta

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

Hermes Agent v0.14.0 'Foundation' Lands: Grok OAuth, OpenAI-Compatible Proxy, PyPI, Native Windows Beta, and 155K Stars

# world-models

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Agora-1: Odyssey's Multi-Agent World Model Lets AIs and Humans Share a Single Simulated Reality in Real Time

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

Hermes Agent Performance Sprint: Adaptive Polling Cuts 1+ Second Per Turn, xAI Web Search Lands, and Security Hardening Touches Down

# xgrammar

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

XGrammar-2: 80x Faster Structured Generation That's Quietly Powering the Next Generation of AI Agents

# zendesk

Zendesk: AI Agents Now Available to Every Customer

Zendesk: AI Agents Now Available to Every Customer

# zero

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

Vercel's Zero: A Compiler That Speaks JSON — The First Programming Language Built for AI Agents

# zero-day

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

Anthropic Launches Project Glasswing — Claude Mythos Preview, $100M Cyber Defense Initiative with AWS, Apple, Google, Microsoft, and NVIDIA

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw

The First AI-Written Zero-Day — Google Confirms Criminal Hackers Used AI to Find a Critical Software Flaw