Organization repository on GitHub
Typed judgment CLI for the Jev model (TypeSafe System One): state + questions in, calibrated answers and exit codes out
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jev CLI — model-clis
A stateless Rust CLI for typed semantic judgments with the Jev model: state and questions in, calibrated answers and exit codes out, as stable JSON on stdout. Ships with an Agent Skill for scripts, CI and agent workflows.
- Stars
- 0
- Language
- Rust
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- model-clis
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev CLI — shaharia-lab.
Used inJev for Software & DevTools
Highlights
- One-question shortcuts — jev noul, jev choice, jev score — read state from --state or stdin and print the answer under id q.
- Full requests come from a file, stdin or a preset: jev ask request.json, cat request.json | jev ask -, or --preset triage with --param.
- Every judging command takes --assert EXPR: false exits 3 after printing the JSON, and an unevaluable expression exits 1 so a broken gate never passes silently.
- jev login stores the key at ~/model-clis/jev/credentials.json (mode 600); JEV_API_KEY takes precedence for CI and containers.
- Installers verify SHA-256 and use GitHub Release assets: brew tap model-clis/packages, scoop bucket, curl or the npx skills add command.
Quickstart
bash
brew tap model-clis/packages
brew install jev
jev login
echo "$LOG" | jev noul "Does this stack trace indicate an out-of-memory kill?" \
--true "OOM killer or cannot allocate memory" --false "Any other failure"Watch out
Grounded in the truncated repo README and GitHub metadata read on 2026-10-15; the excerpt ends mid-example inside the assertions section. The CLI pins jev-latest, so behaviour can shift with the model release, and the README publishes no accuracy or pricing figures.
Questions about this entry
Short answers drawn from the linked project or page.
A stateless command-line tool for typed semantic judgments with the Jev model (TypeSafe System One), plus an Agent Skill for using those judgments in scripts, CI and agent workflows. You provide a state and typed questions; it returns calibrated probabilities and typed answers.
The CLI prints stable JSON on stdout, diagnostics on stderr, and exit codes you can branch on. Every judging command accepts --assert EXPR, evaluated against the response envelope (model, answers and usage).
When the expression is false, the command still prints the full JSON on stdout and exits 3. When it cannot be evaluated — unknown path, type mismatch — it exits 1, because a broken gate must never pass silently.
Several ways: npx skills add model-clis/jev for the skill, brew tap model-clis/packages then brew install jev on Apple Silicon macOS, Scoop on Windows, or the install scripts. Installers fetch GitHub Release assets, verify SHA-256 and default to ~/.local/bin.
Run jev login in your own terminal — never paste the key into a chat. The key is stored at ~/model-clis/jev/credentials.json with mode 600 on Unix. For CI, containers and headless automation, set JEV_API_KEY instead; it takes precedence over stored credentials.
jev ask can read requests from a file or stdin, or use a preset such as triage or review-gate with --param. @PATH arguments keep JSON files structured and treat any other file as text, so state can come straight from a ticket or a README.
The CLI pins the model to jev-latest, the most recent stable release, so answers follow the hosted model's current behaviour rather than a frozen snapshot. JEV_API_BASE can override the endpoint (default https://api.typesafe.ai) for testing or proxies.
More Jev resources like this
A Rust CLI and service for log triage at ingest: it collapses a stream into Drain templates, asks Jev a policy-driven set of typed questions once per new pattern, and routes every line to page, ticket or log.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
tpateeq/tocsinRust
tpateeq/tocsinRustA Rust CLI that reads completed Claude Code and Codex sessions, scores each turn with Jev, and turns recurring patterns into suggested edits for your AGENTS.md, skills and tools. Ships as jta with init, analyze and report commands.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
hobbs/jev-turn-analysisRust
hobbs/jev-turn-analysisRustAn open-source, local-first model router for coding harnesses: Jevia asks Jev for a capability tier per task, applies your safety policy, and keeps recorded execution history in your project or database so later routes learn from outcomes.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
assistant-ui/jeviaRust
assistant-ui/jeviaRustGo CLI for Jev with noul, choice, score, eval, rank, and models commands: rank sends one Score question per item per weighted YAML dimension in a single request and sums weight times score in code, while threshold flags turn a failed gate into exit code 10 for scripts and CI.
Jev Tools & CLIs#community#cli#go
Community
saembit/jeff-cliGo
saembit/jeff-cliGoA Nushell plugin that brings TypeSafe Jev structured decisions into the shell: Nu builds the state and processes the typed answers, the plugin sends the request, and native commands like where and sort-by handle the rows.
Jev Tools & CLIs#community#github#nushell
Community
gleb-chipiga/nu_plugin_jevRust
gleb-chipiga/nu_plugin_jevRustA 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.