Why use this instead of prompting a chat model in scripts?

An LLM returns sentences you must parse and may reword tomorrow. Jev returns numbers in a fixed contract with free output-side economics, so scripts can branch without parsing prose.

How do exit codes and abstain bands behave in CI?

Zero means success with the gate holding, ten means the gate evaluated false, and eleven marks the abstain band. Stdout stays data while diagnostics go to stderr for stable automation.

What catches come from Jev reading questions literally?

It reads literally and cannot count, do arithmetic or compare dates. Phrase questions around properties, route numeric checks to code, and send borderline cases to a person.

Is this an official TypeSafe tool and where does my key go?

No, it is unofficial and community-built. Supply a TypeSafe key by environment or local login, never as a flag, and only short key suffixes are ever displayed.

How do I install the jev CLI?

Several ways: the install script for Linux and macOS, which never uses sudo and checks the download's SHA-256 plus its minisign signature when available; the PowerShell script; brew install shaharia-lab/tap/jev; cargo binstall jev-cli; or cargo install jev-cli --locked.

What do the three question types take, and what limits apply?

noul returns the probability of yes from 0 to 1, choice returns the winning option with its confidence and a probability for each of up to 255 options, and score returns a position on a described scale of 2 to 10 levels with a confidence. A probability near 0.5 means the model cannot tell, not medium intensity.

How do I ask several questions in one call?

Write them in a YAML file with type noul, choice, or score and run jev eval -f triage.yaml --state-file ticket.txt. Extra questions cost tokens, not round trips, and the content is paid for once. jev validate checks the file for free and sends nothing, and jev eval --dry-run prints the exact request and its expected cost.

CommunityJev Agents & MCP

Jev CLI — shaharia-lab

Rust terminal tool that asks Jev noul, choice and score questions about piped text or files and returns calibrated probabilities with stable exit codes for shell scripts, CI jobs and agents.

See highlights

Open github.com

Stars: 35
Language: Rust
License: APACHE-2.0
Published by: Community
Author: shaharia-lab
Last verified: Oct 2026

shaharia-lab/jev-cli

Organization repository on GitHub

View on GitHub

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.

Forks: 4
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

jev is a command-line tool for TypeSafe AI's Jev model, the model that never writes text. Send it some content and a question you defined, get a calibrated probability, and branch on it in a shell script, a CI job or an AI agent. It is a semantic if statement for your terminal. Quick start · What can I use it for? · Documentation · Command reference · FAQ. It takes two seconds, and it is how the next person finds jev. Ask a question, get a probability, branch on the exit code, then ask several questions at once.

Quoted from the project's README. Read the full README.

Tagscommunity jevbest catalog-import awesomejev

Works forJev for Classification Jev for Tool calling

Used inJev for Software & DevTools

Languages: Rust

Highlights

Three typed primitives with confidence, probabilities and multi-question single-call eval files.
Gating flags, dry-run cost preview, batch runs with resume, and JSON or field-only output.
Script-first contract with documented exit codes and separated data and diagnostic streams.
Signed install paths via script, Homebrew or Cargo with key handling that avoids shell history.

Watch out

Community-built and unaffiliated with TypeSafe, requiring your own API key. Jev reads literally and cannot count, calculate or compare dates, so keep that logic in your code. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

Other listings of this project

Forks and copies of this project in the directory. This entry is the canonical one.

jev-cli

An unofficial Python CLI and stdio MCP server for Jev: send text or JSON state with typed questions and get machine-readable noul, choice, or score answers from the official API, OpenRouter, Vercel, or a proxy.

Jev Tools & CLIs#community#python#cli

Community

tumf/jev-cliPython

jev-cli

Command-line toolkit that wraps Jev judgments into scriptable verify, screen, classify, extract, find, rerank, match, route, ask, compact, and batch commands.

Jev Agents & MCP#community#jevbest#catalog-import

Community

Nasrallah-AL/jev-cliTypeScript

jev-cli

A Python CLI wrapper for calling TypeSafe Jev from the terminal, surfaced through a Show HN post in the launch week.

Jev Tools & CLIs#community#python#cli

Community

joshLong145/jev-cliPython

jev-cli

Bun CLI for Jev judgments: evaluate a mixed question map in one call at the root, or use choice, noul, and score shortcuts that print shell-friendly scalar values.

Jev Tools & CLIs#community#github

Community

andrueandersoncs/jev-cliHTML

jev-cli

A CLI that sends state plus typed questions to Jev and prints structured JSON, with boolean, choice and score question types, a documented exit-code contract for CI, and an optional Vercel AI Gateway transport.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

jtsang4/jev-cliTypeScript

jev-cli

A thin Node CLI over the System One API: pass a state string and a question map, get typed answers with probabilities, confidence, latency and token counts back as JSON, one at a time or through a batched worker pool.

Jev Repos & SDKs#community#jevbest#catalog-import

Community

lhotwll217/jev-cliTypeScript

More Jev resources like this

jev-recruiter

Local LinkedIn recruiting workspace on Browser Use's Jev Ultrafast: Jev screens titles, drives navigation, and assesses profile excerpts against your brief while a live browser stays visible; matches and evidence export as JSON.

Jev Agents & MCP#community#jevbest#catalog-import

Community

skeptrunedev/jev-recruiterPython

jev-skill-suggester

Codex Skill plus stdlib-only Python CLI that recommends which installed skill to read next for a task, allowing no-skill or uncertain answers and never executing candidates.

Jev Agents & MCP#community#jevbest#catalog-import

Community

win4r/jev-skill-suggesterPython

jev-judge-mcp

MCP server over stdio that gives coding agents fourteen Jev judgment tools, turning evidence plus an enumerable question into auto, review, or escalate actions from calibrated probabilities.

Jev Agents & MCP#community#jevbest#catalog-import

Community

PyModel/jev-judge-mcpPython

jev-agent-design-with-topk-logits-choices

Research runtime that pages a large logical tool and context space through a small bounded Jev decision surface with explicit approvals.

Jev Agents & MCP#community#jevbest#catalog-import

Community

6Mikao9/jev-agent-design-with-topk-logits-choicesPython

JevLoop

Runnable agent harness that moves pick, score and yes-no loop choices to Jev or Laya in milliseconds while reserving the language model for writing, compiling DECISION.md into executable questions.

Jev Agents & MCP#community#jevbest#catalog-import

Community

zjunlp/JevLoopTypeScript

patdown

Node CLI that lints a file tree against fuzzy natural-language rules in one Markdown file, judging each matched file with a swappable TypeSafe-backed judge.

Jev Agents & MCP#community#jevbest#catalog-import

Community

tyler-dot-earth/patdownTypeScript

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai