OpenWork
Open-source Claude Cowork alternative built on OpenCode; per list notes, its eval testkit uses Jev as a verification judge.
Overview
OpenWork is a free, open-source desktop app for macOS, Windows and Linux where AI agents do real work on your files, positioned as an alternative to Claude Cowork and Codex. Built on OpenCode, it works with 50+ providers, your own keys or local models via Ollama, keeps files local, and lets teams share skills and MCP servers. An OpenWork MCP can be added to Codex, Claude Code or Cursor to reuse the same setup, and the team control plane can be self-hosted.
Per the list summary, OpenWork wires Jev into its eval testkit as a verification judge, so agent-produced work is gated by typed verdicts rather than a text model. The fetched README excerpt does not describe the testkit, so the questions are inferred.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does the agent's output meet the eval's expectation?(inferred) | pass · fail |
How it works
- Run an agent task in the eval testkit.
- Ask Jev a typed verification question about the output.
- Pass or fail the test based on the verdict.
Strengths
- Typed verdicts instead of free-text judging in evals.
Caveats
- Jev usage details only from the list summary.
- Testing integration, not a user-facing feature.
Getting started
Download OpenWork from https://openworklabs.com/download.At a glance
- Type
- Project
- Status
- production
- Language
- TypeScript
- Runtime
- desktop app, MCP server
- Has code
- yes
- Has tests
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
Engineering workflow: wires Jev into its eval testkit as a verification judge so agent-produced work is gated by typed verdicts rather than a text model.
yibie/awesome-jev
Frequently asked questions
How does OpenWork use Jev?
As a verification judge in its eval testkit, per the list summary.
What is OpenWork?
A desktop app where AI agents work on your files, built on OpenCode.
Is it free?
Yes, the desktop app is MIT-licensed.
Related projects
Windows Codex hook that audits a conversation's recorded execution with Jev and answers yes/no questions like 'Did the tests pass?'.
ProjectbetaPowerShellUnofficial Claude Code plugin that checks 'done' claims and small judgment calls with Jev, logs receipts, and can warn on unverified stops.
PluginbetaCLI that grades the coding-agent sessions on your disk (Claude Code, Codex, opencode, Gemini CLI) with Jev for cents.
CLIbetaTypeScriptAgent observability platform that finds and fixes agent failures, with an optional Jev preclassifier for conversation checks.
ProjectproductionTypeScriptClaude Code plugin and CLI for the Jev funnel: judge items in bulk, settle confident ones in code, send only uncertain ones onward.
PluginbetaPythonClaude Code Stop hook that checks an assistant's claims against what it actually read this session using Jev, blocking unsupported ones.
HookbetaPython