Orca
An open-source desktop app for running coding agents such as Claude Code and Codex in parallel, each in its own git worktree.
0 members list Orca, unchanged over the last 12 weeks, data as of 14 November 2026
Members who list Orca in their Stack, by week.
Members who list Orca
Be the first to add Orca
Nobody on Stackness runs Orca yet. Add it to your stack and you're the first member running it.
About Orca
Orca is an Agent Development Environment (ADE) that allows developers to run multiple coding agents in parallel, each isolated in its own git worktree. It supports various agents including Claude Code, Codex, Gemini, and Cursor CLI, providing an integrated interface with terminals, code diffs, a browser, and command-line tools. The platform is designed to streamline workflows with AI-assisted development by orchestrating multiple agents simultaneously rather than working with a single tool at a time.
Oorca is developed by stablyai and released under the MIT license as free and open-source software. It is available as a desktop application for macOS, Windows, and Linux, with companion mobile apps for iOS and Android. The tool includes features for task automation, git integration, and project management to help developers coordinate agent work across multiple branches and environments.
Checked 10 November 2026.
Nobody on Stackness runs Orca yet.
Sign up and add itPosts about Orca
- Running coding agents in parallel git worktrees: the setup, and the merge check git skips
One worktree per agent, then the tests on a trial merge of every pair: in one study, a third of merge conflicts were merges git had called clean.
- Runaway subagent cost in coding agents: what the $78,000 Codex report shows, a test for each cause and the caps that hold
Runaway subagent bills come from nesting no cap stops and children that inherit the parent's model. Count spawn depth in the logs, then cap it in three places.
- Manage multiple coding agents from one workspace: Orca, Offrun, Pi pod and four other options compared
Orca is the pick for most: MIT, three desktop platforms, a worktree per agent and quota per account. Seven ways to manage several coding agents, compared.