Free & open source / Built for builders

Your ideas.
Working in parallel.

One workspace. Multiple AI coding agents. Each in its own git worktree. You choose what ships.

macOS & Linux · Your agents. Your editor. Your code.

parallel code / your next big thing A workspace for every task

Your favorite agents. One place to run them.

  • Claude Code
  • Codex CLI
  • Gemini CLI
  • Copilot CLI
  • Antigravity CLI
Open source. MIT licensed. Yours to build with.

The process / 01—03

From prompt to reviewed code.

Give each idea room to run. Follow the work, inspect the result, and decide what lands in your codebase.

  1. Define

    Create a task

    Describe what you want built and choose an agent: Claude Code, Codex CLI, Gemini CLI, Copilot CLI, or Antigravity CLI.

  2. Run

    Give it its own workspace

    Parallel Code creates a branch and worktree for the task, so agents can work in separate working copies.

  3. Review

    Keep the changes you want

    Inspect the diff and changed files, then merge the branch from the sidebar when you're ready.

Parallel, with purpose

A better way to keep work moving.

One workspace for the moving parts of your day, from routine fixes to competing ideas.

01 / Fan out

Divide the backlog

Give separate tickets to separate agents. Each task has its own worktree and branch, with a diff you can review on its own.

02 / Keep moving

Run work in the background

Send one agent after a flaky test while another builds the next feature. Follow both without waiting at one terminal.

03 / Compare

Try two approaches

Give the same problem different directions. Compare the resulting diffs and choose the solution that fits.

Built for your workflow

All the control. More room to build.

The tools you already trust, with a clearer way to manage agents, branches, and results.

01

Terminal or chat

Run agent CLIs in real terminals, or use built-in chat for Claude Code and Codex with clear approvals and context usage.

02

Your editor stays yours

Keep working in VS Code, Cursor, JetBrains, or Sublime while Parallel Code manages agents and worktrees.

03

Isolated by default

Each task gets a git branch and worktree, keeping active working copies separate.

04

Parallel tasks

Dispatch multiple agents in the same repository and follow each task as it progresses.

05

Guided tours

Walk through a plan, a changed file, or a whole branch in short steps. Ask follow-up questions at any stop.

06

Mind maps & reasoning graphs

Sketch ideas on a per-task canvas the agent can read and extend, then start a new task straight from any node.

07

Agents that delegate

Let agents delegate subtasks in separate worktrees. Review their results and see what needs your attention in one queue.

08

Desktop to phone

Use keyboard shortcuts at your desk, or follow agent terminals and chats from your phone over Wi-Fi or Tailscale.

09

Open source, MIT licensed

Use your own API keys. Parallel Code doesn't proxy or collect your agent traffic.

Inside the workspace

Less juggling.
More building.

See the whole picture, dive into a task, and review every change. A calmer home for your parallel work.

From task to reviewed codeFull workflow demo 00:47
Agents working, waiting for input, and ready to merge
Agents working, waiting for input, and ready to mergeFull size
One task in focus with its chat, changed files, notes, and shell
One task in focus with its chat, changed files, notes, and shellFull size
Inline review comments you can send back to the agent
Inline review comments you can send back to the agentFull size
A guided tour of what the agent changed
A guided tour of what the agent changedFull size
The agent’s reasoning graph, updated live
The agent’s reasoning graph, updated liveFull size
A mind map with branches linked to live tasks
A mind map with branches linked to live tasksFull size
AI Arena — race agents head-to-head
AI Arena — race agents head-to-headFull size

Less overhead, more ownership

Keep your tools.
Lose the busywork.

Your terminal agents and your editor, with the coordination taken care of.

Managing parallel agents manually compared with Parallel Code
The workflowManaging it yourselfWith Parallel Code
Starting a taskCreate a branch and set up a working copy.Describe the task. Get a branch and worktree.
Following progressSwitch between individual terminal sessions.Keep your agent sessions in one workspace.
Reviewing the resultFind the right branch and inspect its changes.Open the task’s diff and leave inline comments.
Finishing upManage the branch and merge from your terminal.Review, then merge from the sidebar.
Explore tool comparisons

A few more things

Good questions.
Clear answers.

Want to dig a little deeper?

Join the conversation on GitHub
Does it work with my IDE?

Parallel Code is a standalone Electron app. Keep using your preferred editor — VS Code, Cursor, JetBrains, Sublime, whatever you like. It manages the agents and worktrees; your IDE handles the code.

Which AI agents are supported?

Claude Code, Codex CLI, Gemini CLI, Copilot CLI, and Antigravity CLI out of the box. Any CLI-based coding agent that works in a terminal can be used.

How does the isolation work?

Each task gets its own git branch and worktree, so agents do not overwrite the same working copy. Branches can still conflict later if they change the same code; review and resolve those integration conflicts before merging back to main.

What platforms are supported?

macOS (universal .dmg) and Linux (.AppImage or .deb). Download from the GitHub releases page.

Is it free?

Yes. Parallel Code is free and open source under the MIT license. Your API keys stay yours — nothing is proxied or collected.

Your next idea doesn't have to wait

Make room for
what’s next.

Put your agents to work. Keep the final say.

Free & open source · macOS & Linux · MIT licensed