User repository on GitHub
Codex code-search plugin using Jev relevance filtering with auditable token metrics
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Jev Context
A local Codex plugin for codebase search: it runs ripgrep, asks Jev a binary Yes/No relevance question for each candidate passage, and returns those above a probability threshold (default 0.50). Codex can expand results or surrounding context without extra Jev calls.
- Stars
- 1
- Language
- JavaScript
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- zbush
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Languages
- JavaScript
- Platforms
- CLI
- Capabilities
- Open sourceRequires API key
Highlights
- Runs ripgrep and keeps passages where Jev's P(Yes) exceeds min_yes_probability, 0.50 by default; expand_results recovers lower-scoring ones without more calls.
- expand_context reads the surrounding source and the containing function, also without additional Jev calls.
- Records paired filtered/unfiltered payloads and expansion costs so retrieval savings can be reproduced under a named tokenizer.
- Install once for use across local projects: Codex supplies the current workspace per search, so switching repositories needs no plugin reconfiguration.
- Defaults are ask-only and receipts-on; global preferences control automatic Jev use and token-savings receipts.
Watch out
Grounded in the truncated README and GitHub metadata reviewed on 2026-10-15; the excerpt cuts off inside the dependency-install step, the documented walkthrough is Windows PowerShell only and unvalidated on macOS/Linux, and smoke tests used a separate Brotato project whose source and outputs are not included. The README itself calls it an experimental MVP.
Questions about this entry
Short answers drawn from the linked project or page.
A local Codex plugin for when your LLM needs to search across a codebase to build context: it runs ripgrep, asks Jev a binary Yes/No relevance question for each candidate passage, and returns the passages that clear a probability threshold.
Each candidate passage gets one binary relevance question, and passages with P(Yes) greater than min_yes_probability — 0.50 by default — are returned. Lower-scoring passages can be recovered with expand_results from a successful binary filtered search.
expand_results pulls lower-scoring passages back from a filtered search, and expand_context reads surrounding source and the containing function. The README says neither makes additional Jev calls, so the expansions are free of model cost.
Filtered and shadow searches send candidate code and your question to the TypeSafe API and can incur charges, so use them only with code you are authorized to send that service. Local telemetry retains original passages, including withheld code, so keep it private.
Node.js 22 or newer, ripgrep with its rg executable available, Codex installed with local plugin support and the built-in Plugin Creator skill, and your own TypeSafe API key — which is separate from your OpenAI account and can incur charges.
The plugin records paired filtered and unfiltered payloads and expansion costs so savings can be reproduced exactly under a named tokenizer. The README cautions the reported numbers count retrieval response text only — not verified Codex context usage, total task savings or billing reductions.
No. The README calls it an experimental retrieval tool, not a security scanner or a guarantee of complete answers. Relevance judgments can be wrong, ignore rules and filename exclusions do not detect secrets embedded in ordinary source, and withheld code is still retained in local telemetry.
More Jev resources like this
An opencode plugin that turns an agent's small decisions — is this command safe, which tool fits, is this PR ready — into typed Jev questions with calibrated confidences, labelling each answer auto or escalate so the agent knows when to ask for help.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
darwintechlab/openjevJavaScript
darwintechlab/openjevJavaScriptA Claude Code plugin that adds five Jev tools — jev_choice, jev_noul, jev_score, jev_ask and jev_doctor — so small decisions like safety checks, tool choices and review verdicts come back as typed answers with calibrated confidence, labelled auto or escalate.
Jev Integrations & Adapters#community#catalog-import#logicrw
Communitydarwintechlab/claude-jevJavaScript
darwintechlab/claude-jevJavaScriptRoute OpenAI Codex CLI turns through Jev: a local loopback Responses API proxy asks Jev to pick a Codex model and reasoning effort for each fresh turn, then forwards the request. If Jev is unavailable, Codex continues unchanged.
Jev Integrations & Adapters#community#catalog-import#madewithjev
Community
tiandee/codex-jev-routerJavaScript
tiandee/codex-jev-routerJavaScriptA fork of codex-with-chatgpt that adds TypeSafe Jev plus deterministic rules to decide when Codex hands planning, debugging or review to web ChatGPT and when it switches back. Smart switching is off by default, and with it off the tool behaves exactly like the original.
Jev Integrations & Adapters#community#catalog-import#logicrw
Effortlane is a local router for Codex on macOS that picks model and reasoning effort with Jev before each user turn, keeps native ChatGPT authentication, and records routing evidence locally. Shadow mode logs recommendations without changing execution.
Jev Integrations & Adapters#community#catalog-import#logicrw
A Claude Code mod that adds $.jev to the engine interface, letting plugin hooks ask Jev for Choice, Score and Noul answers over one state via TypeSafe, OpenRouter, Vercel, Cloudflare, LiteLLM or a custom endpoint.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
chrishan17/claude-jev-modTypeScript
chrishan17/claude-jev-modTypeScriptFrom 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.