stablyai/orca

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 27 minutes ago
Added to GitGenius on June 30th, 2026
Created on March 17th, 2026
Open Issues & Pull Requests: 3,924 (+0)
Number of forks: 3,222
Total Stargazers: 46,095 (+8)
Total Subscribers: 101 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 7.0 hours
Mean response time: 21.4 hours
90th percentile: 46.1 hours
Tracked items: 3,476

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. Only 6% of issues opened in the past year have been closed. Three people close 70% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 1,831
New in 7 days: 477
Closed in 7 days: 226
Avg open age: 12 days
Stale 30+ days: 51
Stale 90+ days: 0

Recent activity

Opened in 7 days: 445
Closed in 7 days: 207
Comments in 7 days: 565
Events in 7 days: 1,392

Top labels

  • bug (1,389)
  • enhancement (902)
  • os:macos (560)
  • os:Windows (364)
  • size/m (305)
  • has_repro (196)
  • P0 (173)
  • pending_repro (138)

Detailed Description

Orca is an application development environment designed for orchestrating fleets of parallel AI agents, built in TypeScript and available across desktop and mobile platforms.

The core functionality of Orca centers on running multiple coding agents simultaneously, each operating within isolated git worktrees. Users can execute agents like Codex, ClaudeCode, OpenCode, or Pi side-by-side and compare their outputs before merging the best results. This parallel execution model is designed to accelerate development workflows by allowing multiple approaches to be explored concurrently. The application supports running agents with users' own API subscriptions, giving developers control over their infrastructure and costs.

The platform includes a mobile companion application available on iOS through the App Store and TestFlight, as well as Android via APK distribution. The mobile app enables users to monitor and steer agents remotely, receive notifications when agents complete tasks, and send follow-up instructions from anywhere. This mobile-first approach extends the IDE experience beyond the desktop environment.

Orca provides terminal functionality comparable to Ghostty-class terminals, featuring WebGL rendering, infinite splits, and persistent scrollback that survives application restarts. The integrated browser includes a Design Mode that allows users to click UI elements in a real Chromium window and automatically send the corresponding HTML, CSS, and cropped screenshots directly into agent prompts. Native integrations with GitHub and Linear enable users to browse pull requests, issues, and project boards within the application, opening worktrees from tasks without context switching.

The platform supports SSH worktrees for running agents on remote machines with full file editing, git operations, and terminal access, including automatic reconnection and port forwarding. Users can annotate AI-generated diffs with comments that are sent back to agents for review and editing before committing. The application includes a VS Code-compatible editor with autosave functionality and supports dragging files and images directly into agent prompts.

Orca CLI provides scriptable access to workflows through commands like worktree create, snapshot, click, and fill, enabling agents to drive Orca itself. Additional features include quick open search across worktrees, files, agents, and commands, account switching with usage tracking for Claude and Codex APIs, rich previews for Markdown and PDFs, and Computer Use capabilities allowing agents to interact with desktop applications.