aicoolies logo
Jean logo
Jean logo

Jean

AI agent dev environment with parallel git worktrees, magic git commands, and Linear integration.

open sourceupdated Jul 20, 2026

Jean is an open-source desktop dev environment for AI agents from coolLabs (the team behind Coolify). It runs multiple coding agents — Claude Code, Codex, and others — in parallel inside isolated git worktrees, each with its own chat session and terminal. Magic git commands handle commits, PR descriptions, code reviews, and merge conflicts with AI assistance, while built-in Linear and GitHub integrations load issue context into every session.

Read our Jean review

A detailed review by the aicoolies team — click to read

Jean is a desktop dev environment built around the idea that AI-assisted development needs more than a chat panel inside an editor — it needs workspace isolation, parallelism, and tight git workflows. The app, from coolLabs (the team behind Coolify), wraps the CLI tools developers already authenticate with — Claude Code, Codex, and others — and runs each agent inside its own automatically-managed git worktree. Sessions, terminals, and chat windows sit side-by-side in one UI, so one agent can fix a bug on a feature branch while another reviews a PR on a separate worktree without changes colliding. The project is Apache 2.0, free forever, with a tested macOS build and Windows/Linux testers wanted.

What sets Jean apart is its opinionated set of git workflows. Magic Git Commands generate AI commit messages, PR descriptions, and release notes; track findings during code review; and resolve merge conflicts with AI — all driven by per-workflow Magic Prompts where the developer picks model and reasoning level (light model for commits, heavier for reviews). The Opinionated pane bundles two token-reduction plugins: RTK proxies CLI tool output to cut 60–90% of tool-output tokens, and Caveman trims Claude responses by ~65–75%. Multi-project and Linked Projects support means related repos auto-inject their CLAUDE.md, AGENTS.md, and docs/ into every session — cross-repo context without copy-paste. Linear is first-class for issue investigation and per-project API keys.

Jean fits the parallel-agent orchestration niche alongside Emdash, Conductor, Sculptor, and Superset. Where some lean terminal-multiplex or pure web UI, Jean sits in the desktop sweet spot: it carries the auth and capabilities of the underlying CLI tools while wrapping them in a UI that makes worktree management and PR workflows visual. Mobile access via localhost, Cloudflare Tunnel, or Tailscale lets developers monitor agents from a phone. coolLabs sustains development through GitHub Sponsors, Open Collective, and managed cloud services — no enterprise tier, no paywalls. For developers juggling multiple AI coding CLIs who want a unified cockpit instead of tmux panes and shell scripts, Jean is a credible open-source option.

Pricing

Free and open source under Apache 2.0. No paid tiers, no enterprise edition. coolLabs sustains development through GitHub Sponsors, Open Collective, and managed cloud services for their other projects.

Platforms

Desktop application. Tested on macOS; Windows and Linux builds available with testers wanted. Mobile access via localhost, Cloudflare Tunnel, or Tailscale.

Categories

Tags

Use Cases

Alternatives

emdash ai sh

Emdash

Top Pick

Open-source agentic development environment for parallel AI agents

Emdash is an open-source agentic development environment for orchestrating many coding agents in parallel. It runs each agent in an isolated Git worktree, presents tasks in a dashboard, auto-detects installed CLIs, works with 25+ agents including Claude Code, Codex, Cursor, Amp and Gemini, and supports MCP server connections for tool access.

Open Source
Conductor.build logo

Conductor.build

Run a team of AI coding agents in parallel on your Mac

Web-based dashboard for monitoring and managing multiple AI coding agent sessions. Provides real-time visibility into what each agent is doing, resource consumption, and task progress across your team. Centralizes agent management so team leads can assign work, review outputs, and track productivity across multiple concurrent AI-assisted development workflows from a single interface.

free
Parallel Code logo

Parallel Code

Run Claude Code, Codex, and Gemini agents in parallel with isolated branches

Open-source desktop app for orchestrating multiple AI coding agents simultaneously. Auto-creates git worktrees per agent and symlinks shared dependencies to prevent conflicts between parallel tasks. Designed for teams and power users who want to run several AI agents on different features or bugs at the same time, maximizing throughput while keeping each agent's changes cleanly isolated.

Open Source
T3 Code logo

T3 Code

Open-source GUI for managing AI coding agents with your own API keys

Unified desktop interface for Codex and Claude Code with a model selector dropdown. Features a git-integrated sidebar, parallel task and thread management, chat and plan modes, and customizable agent access levels. Run via desktop app or npx for instant access. Brings visual project management to terminal-based AI coding agents without sacrificing their command-line power.

Open Source

Related Tools

Grok logo

Grok Build

Top Pick

xAI's terminal coding agent with parallel subagents and worktree-aware automation

Grok Build is xAI's terminal-first coding agent for planning, editing, testing, and reviewing code from a local CLI. The early beta exposes subagent controls, worktree mode, headless JSON output, best-of-N parallel attempts, sandbox profiles, and experimental memory. It fits developers comparing Claude Code, Codex, and Gemini CLI for local agentic workflows with deeper parallel execution.

paid
Claude Code logo

Claude Code

Top Pick

Anthropic's agentic coding CLI

Anthropic's agentic CLI coding tool that delegates complex tasks to Claude directly from the terminal. Understands entire codebases via automatic context gathering, edits multiple files, runs shell commands, and manages Git workflows autonomously. Supports CLAUDE.md for persistent project instructions, integrates with VS Code and JetBrains, and uses Claude Opus/Sonnet with extended thinking for complex architectural decisions. Built for terminal-first developers.

paid
Cursor logo

Cursor

Top Pick

The AI-first code editor

AI-first code editor built as a VS Code fork that deeply integrates LLMs into every part of the development workflow. Features Tab autocomplete with multi-line predictions, Cmd+K inline editing, AI chat with full codebase awareness, and Agent mode for autonomous multi-file edits with terminal execution. Supports GPT-4, Claude, and more with automatic context from project files and docs. Includes privacy mode for SOC 2 compliance. The leading AI-native IDE with 100K+ paying users.

freemiumTelemetry
Codex logo

Codex

Top Pick

OpenAI coding agent for app, editor, terminal, and cloud work

Codex is OpenAI's coding agent for software development across the Codex app, editor, terminal, and cloud tasks. It helps write, review, debug, refactor, and automate code, with ChatGPT plan access for managed surfaces and API-key usage for CLI, SDK, and IDE workflows. The open-source CLI and SDK support local repository work, while cloud features add GitHub review, Slack/Linear integrations, worktrees, skills, MCP, and automations.

freemium
KaibanJS logo

KaibanJS

JavaScript framework for building and visualizing multi-agent workflows on a Kanban board

KaibanJS is an MIT-licensed JavaScript framework for defining AI agents, tasks, tools, and teams, then orchestrating their work through a Kanban-inspired runtime and visual board. It can run inside Node.js, React, or Next.js projects, supports custom UIs and headless workflows, and provides real-time task-state visibility for multi-agent applications.

Open SourceTelemetry
roborev logo

roborev

Continuous local code-review loops for commits produced by AI coding agents

roborev is an MIT-licensed local review system that checks every commit in the background, stores findings in a review queue, and feeds actionable issues back into AI coding sessions. Git hooks, a TUI, branch and dirty-tree analysis, Codex and Claude agent hooks, plus iterative fix/refine commands turn review into a continuous agent workflow.

Open SourceTelemetry

Comparisons

Jean vs Conductor.build — Open-Source Multi-CLI Desktop vs Subscription-Tied Team Dashboard

Jean and Conductor.build both let you run multiple AI coding agents across git worktrees without drowning in terminal tabs, but the trade-offs split sharply. Jean is Apache 2.0 open-source from the Coolify team, auto-detects every coding CLI you have installed, and runs entirely on your machine. Conductor.build is a free closed-source macOS app that wraps your existing Claude or Codex subscription with a team-monitoring dashboard. The right choice depends on whether multi-CLI flexibility and open-source trust matter more than subscription-aware team visibility.