#588 · Primary category： AI Agents & Automation
Orkas
Open-source local-first AI desktop client that orchestrates a team of specialist agents via a commander LLM, with BYO model keys.
Project last updated：08/29/26
GitHub Stars
1.5K
Forks
66
Contributors
9
License
MIT
Why we included this project
Orkas is a desktop app that turns a single chat window into a small team of AI agents. A Commander model takes your goal, breaks it into tasks, and hands them to specialist agents that can run in parallel or one after another, each with its own skills, memory, and context. After each task the agents reflect on what they did and keep the useful skills, so the team gets more capable over time instead of starting from scratch every session. Everything stays on your machine: conversations, files, agent configs, and API keys, and model calls go straight to the provider you bring, whether that is Claude, OpenAI, Gemini, DeepSeek, or one of the other supported options. That makes it a solid choice for teams that want multi-agent orchestration without writing orchestration code or sending data to a hosted platform, and it can hand off to CLI coding agents like Claude Code or Codex when the work is code-heavy.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.