Open-source semantic search makes GitHub issue search 2x faster, 8x more accurate
jamesmurdza · x · 2026-10-23
Developer jamesmurdza open-sourced a GitHub issue semantic search pipeline claiming 2x speed and 8x accuracy over GitHub's native search. It uses Inngest durable workflows to index every issue and comment (millions, with retries/rate limits/checkpoints), a vector store with hybrid search (no rate limits), any local embedding model, and serves results to Claude Code or Cursor over MCP — unlike GitHub's official semantic search, it reads comments too and returns the matching one.
More from coding & agent
- Artificial Analysis launches Coding Agent Index v2.0 with lower scores across the board — ArtificialAnlys · 2026-10-23
- Coding Agent Index v2.0 scores drop across the board: 20 of 21 configs decline — ArtificialAnlys · 2026-10-23
- SWE-Atlas-QnA-AA benchmark: Muse Wonder Full tops revised repo Q&A grading at 68.8% — ArtificialAnlys · 2026-10-23
- FrontierCode v1.1: Opus 5.5 leads at 56%, mid-pack tightly packed at 43–49% — ArtificialAnlys · 2026-10-23
- Artificial Analysis launches Coding Agent Index v2.0: Claude Opus 5.5 leads at 61.7 — ArtificialAnlys · 2026-10-23
- File-Retrieved Tool Output Makes GPT Agents Substitute Approximations, Costing Accuracy — ucriverside · 2026-10-23