Orkas
Orkas is an open-source, multi-agent AI desktop client that builds and orchestrates AI agent teams through conversation.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 1.0k
- Source
- GitHub
- Added
- 2026-08-05
- Last verified
- 2026-08-05
Overview
Orkas is an open-source, locally-first AI work team. It coordinates specialized agents via a powerful commander to accomplish complex tasks. Orkas runs as a desktop application on macOS, Windows, and Linux, keeping your conversations, files, agent configurations, and model keys local—model calls are sent directly to providers. Orkas is ideal for users needing automation of reports, market research, code generation, data analysis, and more.
Key features
- ▪Multi-agent collaboration
- ▪Local-first, data stays on device
- ▪Built-in LLM key management
- ▪Agents with self-evolution capabilities
Use cases
Pros
- ＋Supports multiple LLM providers
- ＋No need to write orchestration code
- ＋Data and keys stored locally
- ＋Agents have self-evolution capabilities
Limitations / notes
- －Requires some learning curve
- －Linux currently requires running from source
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
Yes, Orkas is open-source and free.
Which operating systems are supported?
Supports macOS, Windows, and Linux.
Does it support Chinese?
The README includes a simplified Chinese version, but specific feature support is not clearly documented.
Can it be used commercially?
Yes, Orkas is an open-source project under the MIT license, which allows commercial use.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.