johannesjo/parallel-code

Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

What it solves

Parallel Code eliminates the bottleneck of running AI coding agents sequentially. Instead of waiting for one agent to finish a task before starting the next, it allows developers to dispatch multiple agents in parallel, each working on a separate feature or bug fix without causing git conflicts or blocking the main workflow.

How it works

When a user creates a task, the application automatically handles the environment isolation using git worktrees. It creates a new git branch and a corresponding worktree (a separate directory) for the agent to operate in, symlinking necessary directories like node_modules to save space. It then spawns a supported AI coding CLI (such as Claude Code, Codex, or Gemini) within that isolated environment. Once the work is complete, the user can review the diffs and merge the branch back into the main codebase.

Who it’s for

Developers who use AI coding agents and want to increase their velocity by managing multiple concurrent AI-driven tasks, as well as those who prefer a keyboard-first GUI for managing agent sessions and diff reviews.

Highlights

  • Parallel Execution: Run multiple agents on different features simultaneously in isolated git worktrees.
  • Coded-Agent Integration: Works with existing CLIs like Claude Code, Codex, Gemini, and Copilot.
  • Coded-Tour Generation: Generates guided tours of changes to help users quickly understand complex diffs.
  • Remote Monitoring: Monitor agent progress and provide input via a mobile browser or a dedicated Android app.
  • Environment Sandboxing: Support for project-specific Dockerfiles to run agents in isolated containers.
  • Integrated Tooling: Includes a built-in diff viewer, shell terminals per task, and a live-rendered Markdown canvas.

Related

  • Project
    generalaction/emdash

    Emdash is a cross‑platform desktop app that runs multiple AI coding agents (Claude Code, Codex, Copilot, etc.) in parallel, each in its own Git worktree. It integrates issue trackers, supports remote SSH projects, and keeps all state locally, offering a unified UI for reviewing diffs and merging AI‑generated code.

  • Project
    BennyKok/omg.dev

    omg.dev is an open‑source platform that lets you run coding‑assistant agents (Claude Code, Codex, Copilot, etc.) on your own computer or in the cloud, start tasks from a mobile app, and receive notifications when they finish.

  • Project
    standardagents/dmux

    A tool that manages multiple AI coding agents in parallel by isolating each in its own tmux pane and git worktree.

  • Project
    github/app

    The GitHub Copilot app is a desktop client that lets you run Copilot‑powered AI agents in isolated git worktrees or cloud environments, manage issues/PRs across repos, and automate prompts. It provides visual “canvases” for agent output, parallel sessions, and an “Agent Merge” flow to auto‑merge PRs after checks. Installable on Windows, macOS, and Linux; requires a Copilot plan or your own model key.

  • Project
    timwuhaotian/the-pair

    The Pair is an open‑source desktop app that runs two AI coding agents—a read‑only Mentor that plans/reviews and an Executor that writes and runs code—to cross‑check each other’s work and reduce hallucinations. It supports ten provider CLIs (Claude, Codex, Gemini, etc.) plus local Ollama models, works on macOS/Windows/Linux, offers session recovery, Git integration, resource monitoring, and a rich UI for oversight. Licensed under Apache 2.0.