Jev in production › Search, ranking and matching
Jev Graph Search
Jev reranks shortlisted passages in Obsidian/Logseq knowledge graphs; top-five recall rose from 63.9% to 81.8% on an 8,851-node graph (vendor).
81.8%measured against a baseline, as published by the source
- Use
- Search, ranking and matching
- Industry
- Productivity
- Form
- Open-source tool
- Stage
- In production
- Plugs into
- Obsidian/Logseq
- Listed
- 2026-10-05
- Found via
- github
- Repository
- Emlembow/jev-graph-search
- Stars
- 12
- Forks
- 3
- Last push
- 2026-10-05
- Language
- JavaScript
- License
- MIT
The README opens with
Jev Graph Search helps an AI agent find useful notes and passages in a local Obsidian vault or a folder of Logseq Markdown notes. It makes a shortlist on your machine, then uses Jev to rank those candidates against your question. The result includes the original passage and source reference, so the agent can point back to the note it used.
Run it from the terminal or install the agent skill. An optional JSON snapshot is supported as well. See Jev for the ranking service.
Badge
For the project's own README, linking back here:
Also used for search, ranking and matching
- jegrep $0.01–0.03
- pi-web-search ~2k free uses/month
- Jev RAG 0.444
- oko (bartlomein) 13–44% fewer tokens
- jevsearch 83%
- GStars 1500
- askgrep $0.0049
- genigrep 7%