muster

The AI agent harness you can audit: token-waste ledger, leak-proof scoped memory, eval-gated learning, 20+ LLM providers (Claude, OpenAI, Ollama, Grok, Kimi). TypeScript, MIT. Maintained by musterhq on GitHub, where it has earned 10 stars from the community.

It's actively developed around agent-framework, agent-memory, ai-agents, and is a solid reference for anyone building with these tools.