Interesting repos

Open source AI projects worth an enterprise leader's attention, logged as they surface.

  1. 01 Agent Skills: packaging what your org knows An Apache licensed spec for portable agent capabilities. The enterprise angle is that know-how stops being locked to one vendor's agent.
  2. 02 Agents Need Eyes: The Verification Layer Is Arriving Chrome ships DevTools as an MCP server for coding agents. It is one of the clearest signals that verification, not code generation, is where agentic delivery gets decided.
  3. 03 Astryx: Meta Makes the Design System the Agent Contract Meta's new open source design system calls itself agent ready. That phrase is the strategy: components as the guardrails agents build UI through.
  4. 04 OpenAI Shipped a Codex Plugin for Claude Code. Read the Signal. The official codex-plugin-cc repo lets Claude Code users run Codex reviews and delegate tasks. The interop matters more than the feature.
  5. 05 Graphify Turns Your Repo Into a Knowledge Graph Agents Can Query An open source skill that maps code, docs, and media into a queryable graph for coding agents. Context retrieval is the real constraint on agent quality.
  6. 06 A joke repo just made the best point about token economics Caveman, a Claude Code skill that cuts about 65 percent of tokens by talking like a caveman, went viral. The punchline is a real budget line.
  7. 07 Pentesting is becoming a pipeline stage Strix, an open source AI pentest agent, is trending. The interesting question for enterprises is not the tooling, it is who approves what the agent attacks.
  8. 08 Superpowers: agentic skills as an operating methodology A 245,000-star framework for giving coding agents reusable skills. The signal is that agent capability is becoming a managed artifact, like code.