parallel-code

Screenshots

Multiple agents in parallel	Focused view on a single task
Diff review with inline comments	AI Arena — race agents head-to-head

Why Parallel Code?

• Use the AI coding tools you already trust — Claude Code, Codex CLI, Gemini CLI, and Copilot CLI — all from one interface.
• Free and open source — no extra subscription required. MIT licensed.
• Keep every change isolated and reviewable — each task gets its own git branch and worktree automatically.
• Run agents in parallel, not in sequence — five agents on five features at the same time, zero conflicts.
• See every session in one place — switch context without losing momentum.
• Control everything keyboard-first — every action has a shortcut, mouse optional.
• Monitor progress from your phone — scan a QR code, watch agents work over Wi-Fi or Tailscale.
• Ask about code with any LLM — the inline code Q&A feature supports Claude Code (default) or MiniMax M2.7 (204K context) — configurable in Settings.

How it works

When you create a task, Parallel Code:

1. Creates a new git branch from your main branch
2. Sets up a git worktree so the agent works in a separate directory
3. Symlinks node_modules and other gitignored directories into the worktree
4. Spawns the AI agent in that worktree

When you're happy with the result, merge the branch back to main from the sidebar.

• Tiled panel layout with drag-to-reorder
• Focus mode — single-task layout with a clean two-column view on wide screens (Ctrl+Shift+F)
• Built-in diff viewer with inline review comments and per-commit navigation
• Steps tracking panel — engineering-manager-style timeline of agent progress (writes to .claude/steps.json)
• Notes panel per task — jot ideas, then send the notes straight to the agent as a prompt
• PR CI status watcher — desktop notification when GitHub checks settle
• Shell terminals per task, scoped to the worktree
• Direct mode for working on the main branch without isolation, plus support for folders without a git repo
• Existing worktree import — bring already-created worktrees into Parallel Code
• Sandboxing with project-specific Dockerfiles — drop a .parallel-code/Dockerfile into the project and tasks run inside it
• Coverage radar — per-file test-coverage badges in the Changed Files panel
• Configurable keyboard shortcuts with per-agent presets
• 10 themes — Islands Dark, Minimal, Graphite, Midnight, Classic, Indigo, Ember, Glacier, Zenburnesque, Workbench
• State persists across restarts
• macOS and Linux

Demo

Getting Started

1. Download the latest release for your platform from the releases page:

   • macOS — .dmg (universal)
   • Linux — .AppImage or .deb

2. Install at least one AI coding CLI: Claude Code, Codex CLI, Gemini CLI, Antigravity CLI, or Copilot CLI

3. Open Parallel Code, point it at a git repo, and start dispatching tasks.

Antigravity (agy) signs in interactively and caches credentials in your OS keyring (Keychain/libsecret). The keyring cannot be reached from inside a Linux container — it needs a secret-service daemon the agent container doesn't run — and agy has no API-key fallback, so Docker-isolated Antigravity tasks cannot authenticate. Run Antigravity as a native (non-Docker) task.

The bundled image still ships the agy binary, and ~/.gemini/antigravity-cli (settings/plugins) is shared when "Share agent auth" is enabled, so Docker support is forward-compatible if a file-based or API-key auth path appears later.

git clone https://github.com/johannesjo/parallel-code.git
cd parallel-code
npm install
npm run dev

Requires Node.js v18+.

Ctrl = Cmd on macOS.

If Parallel Code saves you time, consider giving it a star on GitHub. It helps others find the project.

License

MIT