Every
CLI that asks one yes/no question of every function in a codebase with Jev and ranks them by probability: grep whose pattern is a question.
Overview
every asks a yes/no question of every function in a codebase and returns ranked answers. It is not embedding search: rather than finding code similar to your words, it judges the question against each function and returns the probability that the answer is yes, for example "catches an exception and then ignores it". Hits above a threshold (0.75 in the example) are listed with file, line and function name.
It runs on Jev, which the README credits with making this cheap and fast: about seven cents and fifteen seconds for 5,000 functions, and a measured 1,302 functions of gin-gonic/gin in 3.7 seconds for $0.018. A selftest runs 20 labelled functions and prints recall, false positives and AUROC. The source of every scanned function is sent to TypeSafe; the local cache stores only hashes and scores. A hosted tier waitlist exists for people without a Jev key.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this function do what the question describes? | yes · no |
How it works
- Parse the codebase into functions
- Ask Jev the question for every function in batches
- Rank functions by probability
- Show hits above the threshold
Strengths
- Semantic search by judgment rather than similarity
- Low cost and fast as measured
- Built-in selftest with AUROC
Caveats
- Sends function source to TypeSafe
- Requires a Jev key
Getting started
pip install every-cli, export TYPESAFE_API_KEY, every --selftest, then every "<question>" ./path.At a glance
- Type
- CLI
- Status
- beta
- Language
- Python
- Runtime
- CLI
- Has code
- yes
- Has tests
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
Semantic code-search CLI: a yes/no question against every function, ranked by Noul probability.
AnotiaWang/awesome-decision-modelsAsk a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.
logicrw/awesome-jev-projectsAsk a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.
hellogumbo/awesome-jev
Frequently asked questions
Is it embedding search?
No, it judges the question against every function and returns a probability.
How much does a scan cost?
About seven cents for 5,000 functions, per the README.
What leaves my machine?
The source of each scanned function, sent to TypeSafe.
Related projects
Neovim plugin that asks every function in the buffer a plain-language question with Jev and lists hits in quickfix ranked by probability.
PluginbetaLuaSemantic grep that asks Jev a yes/no about every function for questions no regex can express, with cost reporting.
ProjectbetaDeterministic code-graph context for coding agents on Postgres, AGE and pgvector, with optional Jev or local re-selection of symbols.
MCP serverbetaPythonClaude Code plugin that adds Jev as an independent judge for review findings, debugging hypotheses, design options and search hits.
PluginbetaPR reviewer where Jev answers a Clean Code question set for every changed file and a writing model turns the verdicts into review prose.
ServicebetaTypeScriptRetrieval layer for Codex that finds evidence locally, optionally ranks sanitized excerpts with Jev, and returns bounded, cited evidence.
Projectbeta