Jean

On your own server, Jean runs a team of AI coding agents, each in its own git worktree, and lets you steer them all from a browser tab. Every task starts from real context: a GitHub issue, pull request, workflow run, Dependabot alert, security advisory, Linear ticket, Sentry error, or a plain prompt. Jean creates an isolated worktree with its own chat sessions, terminal, and diff, so several agents can edit one repository without colliding. Choose the backend per task from Claude, Codex, Cursor, OpenCode, Pi, Command Code, Grok, and Kimi Code, using your own subscriptions and CLI logins. Plan, Build, and Yolo modes, plan approval, and session recaps keep long runs reviewable. Magic commands handle commits, pull request descriptions, AI code review with tracked findings, merge conflict resolution, and release notes, and every prompt is editable with its own model and reasoning effort. A split or stacked diff viewer covers uncommitted changes, branches, commits, and checkpoints, with line comments. Mr. Robot, a beta sweeper, polls open issues and drafts plans in fresh worktrees. Linked projects share context across repositories, and MCP servers can be switched on per project or per session. Token-protected web access works from a laptop or a phone, and the desktop app can attach to the same server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Jean
Jean
Jean
Jean
Jean
Jean
Jean

Benefits

  • Parallel agents without branch collisions
  • Every task gets its own git worktree with separate sessions, terminal state, and diff, so Claude, Codex, and other agents can work on one repository at the same time without overwriting each other.
  • Start from real repository context
  • Sessions begin from GitHub issues, pull requests, workflow runs, security alerts, Linear tickets, or Sentry errors, and Jean creates the worktree and launches the matching investigation flow for you.
  • Use the agents you already pay for
  • Jean drives your own Claude, Codex, Cursor, OpenCode, and other agent CLIs with your own logins, so there are no extra model fees, usage limits, or locked features.
  • Reach your workspace from any browser
  • The server delivers the full interface over HTTP and WebSocket with token authentication, so you can check on long-running agents from a laptop or phone behind a reverse proxy or Tailscale.

Features

  • Git Worktree Isolation
  • Each issue, pull request, or manual task gets its own worktree with labels, diff stats, PR status, and archive or restore controls, keeping parallel agent work cleanly separated.
  • Multi-Backend Agent Sessions
  • Run Claude CLI, Codex CLI, OpenCode, Cursor Agent, Pi, Grok, and Kimi Code with Plan, Build, or Yolo modes, per-session models, MCP servers, and session recaps.
  • Magic Commands and Prompts
  • One-key commands commit, push, open pull requests, review code, resolve conflicts, and write release notes; each prompt template carries its own backend, model, effort, and mode.
  • Diff Review and Terminals
  • Review changes in a split or stacked diff with line comments, browse project files, and dock xterm.js terminals beside each session without leaving the browser.
  • Mr. Robot Issue Sweeps
  • A beta mode polls open GitHub issues with label filters and active hours, creates a worktree per issue, drafts a plan, and can execute plans you approve.
  • Headless Server Deployment
  • The jean-server binary runs as a systemd service or a ghcr.io Docker image with token authentication, /healthz and /readyz probes, and Caddy or Nginx reverse proxy support.

Apps Similar to Jean