awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
stablyai avatar

stablyai/orca

0
View on GitHub↗
orca.dev
↗

Orca

Orca is a cross-platform desktop workspace for running several terminal-based coding agents at once on a single repository. Each agent runs in its own embedded pane and gets its own isolated Git worktree, so parallel edits don't overwrite one another and merge later through normal Git. It hosts any command-line coding agent under the user's own subscription and credentials, and it shows how much of each agent's usage limit has been consumed and lets the user switch accounts without logging out.

Orca also supports lead-and-helper delegation: one agent splits a large task, spawns workers in separate workspaces, and gathers their results for review. A session can be shown as a chat interface or as the raw terminal and moved between the two without losing context. Every app action is available from a command line, so agents and scripts can create worktrees, start workers, drive the browser, and schedule automations. Agents can also operate desktop applications and external browsers when no command-line tool or programming interface exists for the task.

Around the agents, the workspace covers review and project flow. Users can read agent changes in side-by-side diffs, leave notes on exact lines, and send feedback or failing checks back to the agent. Commit messages and pull requests can be drafted from the diff. Tasks from GitHub and Linear can each start a dedicated workspace, and saved prompts can run on a recurring schedule for chores like dependency updates, issue triage, and flaky-test sweeps.

Workspaces are arranged in resizable split panes holding agents, terminals, browsers, and diffs. The built-in browser can capture the HTML, styles, and selector of a clicked element for use in a prompt, and community plugins add themes, editors, languages, and panels. Agents can run on SSH hosts or cloud machines so long tasks continue while the laptop sleeps, and a paired mobile app sends alerts when an agent needs input and allows replies from a phone.

Features

  • CLI Coding Agent Hosts - Hosts any command-line coding agent in a desktop workspace under the user's own subscription and credentials.
  • AI Coding Agent Panes - Hosts several terminal coding agents in separate panes of a desktop workspace, with lead-and-helper delegation and shared review tools.
  • Coding Agent Orchestrators - Coordinates several terminal coding agents in parallel on one repository, with a lead agent delegating to helpers and gathering results.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
118,546 stars·7,526 forks·TypeScript·MIT·3 views
Parallel Agent Runs - Runs several terminal-based coding agents at once on one repository, each in its own embedded pane.
  • Embedded Terminal Panes - Embeds terminals in a cross-platform desktop app that hosts command-line agents and switches between raw terminal and chat views.
  • Worktree Isolation Tools - Gives each agent its own Git worktree so parallel agents edit separate working copies without overwriting each other.
  • Git Worktree Management - Manages a separate Git worktree for each agent so many changes to one repository proceed in parallel.
  • Agent Usage and Account Trackers - Shows how much of each agent's usage limit is consumed and when it resets, and switches accounts without logging out.
  • Worktree Isolation - Gives each coding agent its own isolated Git worktree so several agents work on one repository without interfering.
  • Agent Change Reviews - Shows agent changes in side-by-side diffs, lets users leave line notes, and sends feedback or failing checks back to the agent.
  • Coordinator-Worker Orchestration - Splits a large task across worker agents in separate workspaces and collects their results back for user review.
  • Issue Tracker Task Workspaces - Pulls GitHub and Linear tasks into one list and opens a dedicated workspace for each task when work begins.
  • Split Pane Layouts - Arranges agents, terminals, browsers, and diffs side by side in resizable split panes shaped to the task.
  • Agent Command Line Interfaces - Exposes every app action through a command line so agents and scripts can create worktrees, start workers, and drive the browser.
  • Remote Agent Session Hosting - Runs agent sessions on SSH hosts or cloud machines so long tasks continue while the laptop sleeps.
  • Task Runners and Orchestration - AI orchestrator for running multiple terminal agents side-by-side in git worktrees.
  • Star history

    Star history chart for stablyai/orcaStar history chart for stablyai/orca

    How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

    Frequently asked questions

    What does stablyai/orca do?

    Orca is a cross-platform desktop workspace for running several terminal-based coding agents at once on a single repository. Each agent runs in its own embedded pane and gets its own isolated Git worktree, so parallel edits don't overwrite one another and merge later through normal Git. It hosts any command-line coding agent under the user's own subscription and credentials, and it shows how much of each agent's usage limit has been consumed and lets the user switch accounts…

    What are the main features of stablyai/orca?

    The main features of stablyai/orca are: CLI Coding Agent Hosts, AI Coding Agent Panes, Coding Agent Orchestrators, Parallel Agent Runs, Embedded Terminal Panes, Worktree Isolation Tools, Git Worktree Management, Agent Usage and Account Trackers.

    Which projects share features with stablyai/orca?

    Projects with overlapping indexed features include: hardbeat920/monocode — Monocode is a native desktop application, written in Rust, that runs several installed AI coding agent command-line… mattpocock/sandcastle — Sandcastle is a TypeScript library for launching AI coding agents from scripts or CI pipelines and running them… getpaseo/paseo — Paseo is an LLM coding agent orchestrator and multi-agent workflow manager designed to coordinate multiple AI agents… claude-code-best/claude-code — Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software… builderz-labs/mission-control — Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets… vastsa/pi-desktop — PI-Desktop is a desktop application that runs an AI coding agent on your own machine against a local repository.…

    Projects sharing features with Orca

    These projects share indexed features with Orca. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
    • hardbeat920/monocodehardbeat920 avatar

      hardbeat920/monocode

      3,737View on GitHub↗

      Monocode is a native desktop application, written in Rust, that runs several installed AI coding agent command-line tools from one interface. It reuses each tool's existing sign-in and the user's own subscriptions rather than selling tokens. Sessions live in tabs and split panes grouped by project, and each parallel task can run in its own Git worktree, so several agents can work on the same project without overwriting each other's files. Beyond running a single agent, it supports splitting work across up to four worker agents, handing a session to another model with a recap, and continuing p

      Rust
      View on GitHub↗3,737
    • mattpocock/sandcastlemattpocock avatar

      mattpocock/sandcastle

      8,914View on GitHub↗

      Sandcastle is a TypeScript library for launching AI coding agents from scripts or CI pipelines and running them unattended inside isolated sandboxes. A single programmatic call starts a chosen agent, runs it for a set number of iterations, and returns the commits, branch, and per-iteration results. Sandboxes can be Docker or Podman containers, native operating-system sandboxes (Bubblewrap on Linux, Seatbelt on macOS, with no image or daemon), or cloud providers such as E2B, Modal, and Fly.io Sprites. Agents can also run directly on the host with no isolation. The agent and sandbox layers are

      TypeScript
      View on GitHub↗8,914
    • getpaseo/paseogetpaseo avatar

      getpaseo/paseo

      9,118View on GitHub↗

      Paseo is an LLM coding agent orchestrator and multi-agent workflow manager designed to coordinate multiple AI agents across isolated git worktrees. It provides a unified control interface for managing these agents and their associated environments to execute complex programming tasks. The system distinguishes itself through a remote agent daemon that enables secure access to local coding agents via encrypted relays. It employs a git worktree environment manager to isolate parallel tasks into dedicated directories and branch-based server URLs, preventing file collisions and network port confli

      TypeScriptadeagentsclaude-code
      View on GitHub↗9,118
    • claude-code-best/claude-codeclaude-code-best avatar

      claude-code-best/claude-code

      20,272View on GitHub↗

      Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software engineering. It enables AI agents to perform codebase modifications, debugging, and Git workflow management while coordinating multiple specialized agents to decompose and execute complex engineering tasks in parallel. The system distinguishes itself through a high degree of isolation and safety, utilizing Git worktrees to create independent working directories for concurrent agents and implementing a tiered permission system that combines user rules, project policies, and OS-level

      TypeScript
      View on GitHub↗20,272
    Compare all 30 related projects→