fr: natural-language codebase search with Jev — no LLMs, no embeddings
Arindam_1729 · x · 2026-10-01
The author shares how exploring TypeSafe's decision model Jev led to building fr, a faster way to search a codebase in natural language. No LLMs or embeddings — Jev alone figures out which files matter: ask a question, get the files you need. Same project as the previously released fileroute repo; this post adds the motivation.
Related event: fileroute Open-Sourced: NL Code Search Without LLMs or Vectors(2 posts)→
More from coding & agent
- We shipped 2,000 MCP integrations. Enterprise customers wanted only their own 20 — alexcovo_eth · 2026-10-02
- "The repos are now the prompts, 100%": Ofir Press on AI coding's shifting context — OfirPress · 2026-10-02
- OpenHands announces SOC 2 Type II compliance for enterprise agent security — rajistics · 2026-10-02
- Grady Booch: Coding agents write code well, but architecture still needs human judgment — Grady_Booch · 2026-10-02
- Jev pitches 'decision primitives': models plugging into logic without text — hardimanjames · 2026-10-02
- LangChain's Sproul: agent core pattern unchanged for a year, "we've been at AGI for four months" — BraceSproul · 2026-10-02