The open-source, high-performance AI Agent Observability, Tracing, and Self-Healing Platform. Transparently capture LLM completions, visualize multi-agent swarm topologies, and run sandbox prompt replays.

🔥捕捉编码提示的灵感火花。将它们组合成可复用的配方。在后续任务中回忆并调整——适用于Claude Code、Codex和任何智能体技能宿主。 Capture coding prompt sparks. Compound them into reusable recipes. Recall & adapt on the next task — for Claude Code, Codex, and any Agent Skill host.

Detect API contract drift before it breaks downstream consumers. Bun-first CLI.