User repository on GitHub
Jev-assisted retrieval and evidence-preserving inspection for local Markdown, Obsidian vaults, and Logseq Markdown graphs.
- Forks
- 3
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Tools & CLIs
Jev Graph Search
CLI and agent skill that finds useful notes in a local Obsidian vault or Logseq Markdown graph: it shortlists candidates on your machine, then has Jev rank them against your question and returns the exact source passage.
- Stars
- 12
- Language
- JavaScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- MikeLembo
- Last verified
- Oct 2026
- Languages
- JavaScript
- Platforms
- CLIOpenRouter
- Capabilities
- Open sourceRequires API key
Highlights
- On one 8,851-node tax-code graph, Jev reranking raised top-five source recall from 63.9% to 81.8%.
- Search shortlists keyword matches and linked notes locally, then sends selected titles, bounded aliases, and content excerpts to Jev for reranking.
- Commands cover search, place, audit, and traverse; place and migration commands propose changes without writing to your graph.
- Setup asks you to choose TypeSafe or OpenRouter and saves your key in a private per-user configuration file outside the graph.
- An --offline mode uses local lexical ranking, so the included example runs without any API key.
Quickstart
bash
npx --yes [email protected] jev-graph-search setup
npx --yes [email protected] jev-graph-search search "Why did we choose this database?" --input ./ObsidianVaultWatch out
Copy reviewed against the repository README on 2026-10-15; the README was truncated in the digest, so later configuration sections were not inspected. The 8,851-node tax-code benchmark is a single graph, no other benchmarks are reported, and Logseq database and Org-mode formats are outside the supported interface.
Questions about this entry
Short answers drawn from the linked project or page.
It helps an AI agent find useful notes and passages in an Obsidian vault or a folder of Logseq Markdown notes: it makes a shortlist on your machine, then uses Jev to rank candidates against your question and returns the original passage with its source reference.
Run npx --yes [email protected] jev-graph-search setup with Node.js 20+, choose TypeSafe or OpenRouter, and paste your key into the hidden prompt. For a persistent command, npm install --global [email protected].
On one 8,851-node tax-code graph, top-five source recall rose from 63.9% without Jev to 81.8% with it; top-one rose from 33.2% to 73.2% and top-three from 53.5% to 80.1%.
Obsidian vaults are read recursively including nested folders, and Logseq graphs are supported through their Markdown pages/ and journals/ files. Logseq database and Org-mode formats are outside this interface, and hidden paths and symbolic links are skipped.
Yes. Clone the v0.2.2 tag and run the example with --offline, which uses local lexical ranking instead of Jev; remove --offline after setup to use the ranking service.
Search reads the graph, and the place and migration commands propose changes without writing to it. Results keep the exact source evidence so the agent can point back to the note it used.
Setup saves the key in a private per-user configuration file outside the graph. Installing the agent skill does not configure API keys or read your files by itself.
More Jev resources like this
Obsidian plugin that searches a vault locally and offline with BM25 and no API key, then reranks the top candidates with Jev only after you approve exactly what gets sent. The README reports nDCG@10 rising from 0.53 to 0.88 on 120 queries.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
jh1373/jev-searchJavaScript
jh1373/jev-searchJavaScriptA zero-dependency Node tool that finds where a folder of Markdown notes contradicts itself: crosscheck judges every note pair from both sides, and ask puts one plain-English question to every note and ranks the folder by probability.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
nothans/sieveJavaScript
nothans/sieveJavaScriptWrite end-to-end tests for web apps in plain English; jev-e2e turns each case into a plan, has Jev pick the page controls, and runs it with Playwright, returning PASS, FAIL or BLOCKED with HTML, JSON and masked screenshot evidence.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
perixtar/jev-e2eTypeScript
perixtar/jev-e2eTypeScriptFish-style zsh autosuggestions ranked by Jev instead of prefix matching: as you type, it asks a model which recent command you are most likely retyping and shows the best guess as grey inline text you accept with the right arrow.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
findmalek/guessworkTypeScript
findmalek/guessworkTypeScriptAn npm CLI that scans TypeScript, JavaScript and Python codebases for LLM calls that are really decisions, converts them into Jev modules with confidence-gated fallbacks, and shadow-tests them on recorded traffic before you swap.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
0xjba/jev-swapHTML
0xjba/jev-swapHTMLA bash-native CLI from Parall that gives an agent Jev as an atomic tool: pipe any event stream through a plain-English question and it prints only the lines that pass, composing with the tools your agent already pipes.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
parall-hq/jevableTypeScript
parall-hq/jevableTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.