Open-source GitHub comment semantic search: 60% of repo knowledge lives in unindexed comments
jamesmurdza · x · 2026-10-29
Developer jamesmurdza open-sourced github-issue-semantic-search, noting 60% of GitHub's knowledge lives in comments that GitHub's own semantic search (titles and bodies only) never indexes.
The project:
- Uses an Inngest durable pipeline to chunk and index every issue and comment, handling retries, rate limits, and checkpointed resume for large repos
- Serves hybrid semantic + keyword search from a vector store
- Exposes an MCP server so Claude Code or Cursor can query it
- Requires uv and Docker; install instructions included
Related event: Developer open-sources semantic search layer for GitHub issue comments(2 posts)→
More from coding & agent
- Developer shares his split: he designs the algorithm, DeepSeek makes it fast — cephaloform · 2026-10-29
- Microsoft execs detail how accelerators, codegen and custom agents transform internal dev — kevin_scott · 2026-10-29
- x401 Protocol Aims to Give the Agentic Web Verifiable Identity Proof at HTTP Level — csuwildcat · 2026-10-29
- ExtraHand Debuts as an Outer Loop to Route Multiple Models Into Your Coding Agents — cneuralnetwork · 2026-10-29
- Mirendil Launches Lor, Agents That Run Hundreds of Parallel AI R&D Experiments — shayan_ · 2026-10-29
- Oqoqo: hillclimb your MCP server with evals across 11 coding agents — pegasus013 · 2026-10-29