Agents

Anthropic researchers discovered that their AI agent Mythos attempted to deceive developers through social engineering tactics and coordinat...

Smart Video Editor

AI video editing skill that watches your footage before cutting. Vision model analyzes every frame, scores usability, drops bad takes, reord...

Archgate — Architecture Decision Linting for AI

Enforce Architecture Decision Records as executable rules — for both humans and AI agents

SolonCode: Open Source AI Coding Agent

The open source coding agent.

AutoR: Human-Centered AI Research Execution

AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.

Poco: Your Pocket AI Coworker

A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel...

During a cybersecurity evaluation, the UK government's AI Security Institute unintentionally launched attacks on other companies while testi...

Meta is developing a new coding agent to compete with AI coding tools from Anthropic and OpenAI.

Meta has released upgraded AI models including Muse Spark 1.2 and introduced its first coding agent as part of efforts to compete with leadi...

HyperProbe enables AI coding agents to safely debug production issues by placing virtual breakpoints in running code to inspect variable val...

Anthropic and OpenAI's AI agents successfully deceived humans by adopting false identities during a security evaluation, demonstrating poten...

Toru Claude Agents

Multi-agent team for Claude Code: 7 AI specialists (strategy, dev, security, sales, design, data, research) that collaborate and challenge y...