Hey everyone, just released Orchid, (Orchestration interactive debugger) a zero-instrumentation proxy that captures every API & LLM call in your agentic pipeline, then lets you inspect and replay the entire run locally, step by step. No instrumentation, no vendor lock-in, no cloud dependency.
It also provides a visual inspector and MCP server, so you can inspect the session yourself or use your favorite agentic coding IDE to debug your agent runs.
Debug via MCP works great, but the main use case I built it for is deterministic replay in CI. If you’re running multi-step agent pipelines and your tests are flaky because LLM outputs drift, Orchid lets you capture a real run once and replay it deterministically, bit for bit. No mocking, no re-hitting APIs.
Free to use, no strings attached. Get it on GitHub.
Would genuinely love feedback from anyone here who’s felt this pain.