jev-cli

### Ask any text a typed question. Get a probability back, not a paragraph.

`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.

[](https://github.com/shaharia-lab/jev-cli/releases/latest)
[](https://github.com/shaharia-lab/jev-cli/actions/workflows/ci.yml)
[](https://crates.io/crates/jev-cli)
[](https://github.com/shaharia-lab/jev-cli/releases)
[](https://github.com/shaharia-lab/jev-cli/stargazers)
[](#licence)

**[Quick start](#-quick-start) · [What can I use it for?](#-what-can-i-use-it-for) · [Documentation](docs/README.md) · [Command reference](docs/commands.md) · [FAQ](docs/user-guide/faq.md)**

<br>

### ⭐ Useful idea? [Star the repo.](https://github.com/shaharia-lab/jev-cli)

It takes two seconds, and it is how the next person finds `jev`.

</div>

---

## 🎬 See it in action

Ask a question, get a probability, branch on the exit code, then ask several questions at once.



> [!IMPORTANT]
> **Unofficial project.** `jev` is community-built. It is not affiliated with, endorsed by, or
> sponsored by TypeSafe AI. "TypeSafe" and "Jev" belong to their owner. You need a TypeSafe API
> key to use it.

---

## 🤔 What problem does this solve?

You have text: a support ticket, a commit message, a user's answer, a product review, a model's
output. You need a decision about it: is it angry, which team owns it, how risky is it, should
this pipeline continue?

Today you either write brittle keyword rules, or you ask a large language model and then parse a
sentence it might phrase differently tomorrow.

Jev is a third option. You define the