a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

Agent Skill for complex work: research before asking, ask before planning, plan before building, verify before delivering, independent review before calling it done. Plain text, no runtime.

An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters.

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.