Orkas
Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs your installed coding CLIs — Claude Code, Codex, Op
What is Orkas?
Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs your installed coding CLIs — Claude Code, Codex, OpenCode, OpenClaw, Hermes — as local sessions. Agents self-evolve via reflection and skill crystallization. BYO keys. macOS / Windows / Linux.
Overview of Orkas
What it is
Orkas is an open-source, local-first multi-agent desktop application. It uses a Commander LLM to plan goals and coordinate specialist sub-agents. Nine specialist agents are included with the app. Orkas can also drive external CLI coding agents such as Claude Code, Codex, OpenCode, OpenClaw, and Hermes as local sessions. Users bring their own API keys. It runs on macOS, Windows, and Linux.
Key features
- A Commander LLM that understands context, breaks down goals, and coordinates specialist agents.
- Nine specialist agents ship with the app, including DeepResearcher, ContentWriter, PptMaker, and others.
- Drives external CLI agents (Claude Code, Codex, etc.) as local sessions.
- Local-first design: conversations, files, API keys, and custom agents stay on the user's disk.
- No vendor lock-in: mix different model providers across agents.
- Agents improve through reflection and skill crystallization after each task.
Use cases
- Automate recurring reports and market research: a specialist agent gathers, summarizes, and ships a weekly report.
- Turn a product spec into development tasks: the Commander breaks a PRD into tasks and dispatches them across agents.
- Chat with documents and run local data analysis: drop files in, keep data on the machine.
- Produce code, research, video, and slide decks from one chat by driving open-source tools and CLI agents.
Getting started
See the repository README for installation instructions.
License and pricing
Orkas is licensed under the MIT License. It is open source and free to use.
Based on the project's public README and repository metadata.