v1.0.9 · SEE LICENSE IN LICENSE
Observability and enforcement for AI agent harnesses. 40 built-in policies hooked into 12 of them — Claude Code, Codex, Cursor, Hermes, OpenClaw and more — blocking the tool call before it runs. Local dashboard included, no account needed.
v0.11.0 · MIT
Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.
v0.21.19 · MIT
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
v0.9.25 · MIT
See where your AI spend goes - by task, tool, model, and project
— · Apache-2.0
Persistent memory for AI coding agents, powered by iii-engine's three primitives
v3.2.0 · MIT
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
v1.3.1313 · MIT
Coherence infrastructure for self-evolving AI agents — on the Claude Code or Codex subscription you already have.
v1.17.2 · MIT
One session. Two commands. Full team. Zero meetings.
— · MIT
AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.
— · MIT
Lives inside your Claude Code session. Capture work as structured experience, then render resumes, Korean cover letters, interview answers, and project ideas from it.
— · Apache-2.0
Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.
— · MIT
Real-time execution trace and cost intelligence for Claude Code
— · MIT
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
— · MIT
🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.
v0.32.0 · MIT
Multi-agent workflows with full observability and time travel: watch every step live, rewind, fork, and replay any run. Claude Code, Codex, Gemini, Hermes, OpenClaw, any model or harness.
— · Apache-2.0
Run Codex and Cursor as background workers inside Claude Code. Reviews, tasks, and rescues with tracked jobs, live progress, and session handoffs.
— · MIT
The most expensive bug in AI-assisted building is shipping the wrong thing, well. A CLAUDE.md for PM + eng teams using Claude Code- 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.