# Orca

> Desktop app that runs several coding agents in parallel, each in its own worktree

- Category: Agents & dev (`agents`)
- Tags: `open-source`, `free`
- Official: https://github.com/stablyai/orca
- Wunderlust: https://wunderlust.xyz/r/orca
- Image: https://wunderlust.xyz/media/orca-poster.jpg
- Video preview: https://wunderlust.xyz/media/orca.webm
- Added: 2026-11-05

## What it is

App for orchestrating command-line agents such as Claude Code and Codex, with each agent in its own git worktree and everything tracked in one place.

## What it’s for

For sending the same prompt to several agents, comparing the results and merging the best one, or monitoring agents remotely.

## Benefits

- One prompt to several agents in isolated worktrees
- Design mode: click a UI element and send its HTML, CSS and a capture to the agent
- Diff annotation that goes back to the agent, plus GitHub and Linear PR and issue browsing
- Mobile app for tracking agents and sending follow-ups

## Caveats

- According to the maker, it is an orchestrator for '100x builders'.
- MIT license, free; the page doesn't mention paid plans.

## Similar on Wunderlust

- [Agent Browser](https://wunderlust.xyz/r/agent-browser.md): Tool that gives AI agents web browsing
- [Aurelio](https://wunderlust.xyz/r/aurelio-finance.md): Open source wealth and financial-planning app that runs on your own computer
- [Hermes Agent](https://wunderlust.xyz/r/hermes-agent.md): Open source AI agent from Nous Research that learns skills and runs on your own infrastructure
- [Unsloth Studio](https://wunderlust.xyz/r/unsloth-studio.md): App for running, chatting with and training AI models locally
- [OpenClaw](https://wunderlust.xyz/r/openclaw.md): Open-source AI assistant that runs on your machine and replies through chat apps
- [Strix](https://wunderlust.xyz/r/strix.md): Open source agent that tests app security with exploit attempts and PoCs