OSS Tanbou

Jean — A Tauri development environment for running multiple AI coding CLIs across Git worktrees

OSS health 93
About these scores

Discovery score is an unbounded weighted, log-compressed index of stars, watchers, forks, and contributors. Growth momentum is its change over the observed period; OSS health is a 0–100 score from available repository recency, Community Health, and release data.

Stars
1,281
Primary language
TypeScript
License
Apache-2.0
Repository last updated
Sep 17, 2026

Overview

Jean is a desktop AI development environment for managing Claude CLI, Codex CLI, Cursor CLI, OpenCode, Grok, Kimi Code, and other agents across multiple projects, Git worktrees, and sessions. Built with Tauri v2, React, and Rust, it also integrates terminals, diffs, GitHub/Linear, MCP, and headless Web Access. The latest release checked is v0.1.73.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Parallelize AI coding tasks by separating projects, worktrees, and sessions

Jean can create, archive, restore, and delete Git worktrees, then run multiple sessions inside those isolated work areas. Execution modes, plan approvals, recaps, saved context, and session naming are managed from one desktop interface.

Sources: [2]

Orchestrate existing CLIs instead of locking into one model vendor

Claude, Codex, Cursor, OpenCode, PI, Command Code, Grok, Kimi, and other CLI backends can sit alongside MCP, GitHub issue/PR/workflow tooling, Linear, embedded terminals, Git operations, diffs, and a file browser. Model credentials remain with the underlying CLIs.

Sources: [2]

For developers who want to compare and parallelize coding agents without sharing one working tree

Jean is useful when separate agents should get separate worktrees, or when developers want terminals, diffs, repository investigation, and multiple AI backends in one workspace. Headless server mode also exposes the same UI through Web Access.

Sources: [2]

It is still a 0.1-series project; secure Web Access and each agent's privileges independently

The latest release is v0.1.73. The README says Windows is not fully tested and Linux is community-tested. Web Access uses token authentication, but remote use should be placed behind a private network or TLS-enabled proxy. Each AI CLI can have broad repository and terminal access, so credentials, MCP servers, and high-autonomy execution modes require deliberate review.

Sources: [2][3]

Official sources

  1. [1]coollabsio/jean — GitHub repository metadata(2026-09-17)
  2. [2]Jean — README(2026-09-17)
  3. [3]Jean v0.1.73 release(2026-09-17)
Supplemental curator note

Treat Jean as an orchestration environment for existing agent CLIs rather than another model-specific coding agent.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/coollabsio/jean.git
  2. 2

    Enter the repository

    cd jean
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

1,281 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
137
Open PRs
40

Development activity is still being collected.

Built with

Categories and tags

GitHub data

GitHub dataView detailed GitHub data

GitHub Topics

  • agent
  • ai
  • claude-code
  • worktree
  • git
  • parallel
Stars
1,281
Forks
160
Watchers
4
Open issues
70
Primary language
TypeScript
License
Apache-2.0
Repository last updated
Sep 17, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.