Cherry Studio is a cross-platform desktop AI client that connects to many LLM providers, local models and 300+ preset assistants.
eigent-ai/eigent
Open-source desktop app for running a local multi-agent AI workforce that automates multi-step computer tasks, positioned as a free alternative to Claude Cowork.
Open-source alternative to:Claude Cowork
- Stars
- 15,614
- Forks
- 1,874
- Open issues
- 250
- Last commit
- 21 hours ago
What is it?
Eigent is an open-source desktop application for delegating work to AI agents. Users can run a single agent for focused tasks, or a Workforce mode where several specialized agents divide a complex job, work in parallel, and execute multi-step workflows together.
The app is built on the CAMEL-AI framework and supports MCP integration and agent skills. It ships with built-in browser and terminal toolkits, and it can connect to cloud model APIs or local inference servers such as Ollama, vLLM and LM Studio. A local deployment mode runs the backend on your own machine, while a cloud-connected mode requires an account.
The frontend is written in React and TypeScript inside an Electron shell, with a FastAPI and Python backend managed by uv. The project is Apache-2.0 licensed, and the team also offers a commercial cloud version and enterprise features such as SSO.
Key features
- 01Single-agent mode for focused desktop tasks
- 02Workforce mode where multiple agents run tasks in parallel
- 03Scheduled automation for recurring workflows
- 04Local-first execution that keeps files and credentials on your machine
- 05Model-agnostic support for cloud APIs and local inference servers
- 06MCP and agent skill integration with built-in browser and terminal toolkits
Use cases
- Organizing a cluttered desktop folder into a cleaner structure
- Generating monthly development reports from GitHub pull requests
- Investigating CI failures by fetching logs and producing audit reports
- Running a local model for private automation without cloud accounts
Quick start
- 1
Clone the repository
git clone https://github.com/eigent-ai/eigent.git - 2
Enter the project directory
cd eigent - 3
Install dependencies (Node.js 18-22 required)
npm install - 4
Start the app in development mode (connects to cloud services)
npm run dev
Things to know
- The quick start mode connects to Eigent cloud services and requires account registration.
- The fully standalone local deployment needs a separate server setup guide and local model integration.
- Enterprise features such as SSO are offered under negotiated terms, not in the open-source code.
Topics
FAQ
- What is eigent?
- Open-source desktop app for running a local multi-agent AI workforce that automates multi-step computer tasks, positioned as a free alternative to Claude Cowork. Eigent is an open-source desktop application for delegating work to AI agents. Users can run a single agent for focused tasks, or a Workforce mode where several specialized agents divide a complex job, work in parallel, and execute multi-step workflows together.
- Is eigent free to use? What license does it have?
- eigent is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is eigent still maintained?
- Actively maintained. The last commit to eigent was on Oct 19, 2026.
- What can I use eigent for?
- Organizing a cluttered desktop folder into a cleaner structure Generating monthly development reports from GitHub pull requests Investigating CI failures by fetching logs and producing audit reports Running a local model for private automation without cloud accounts
- How do I install eigent?
- Clone the repository: git clone https://github.com/eigent-ai/eigent.git Enter the project directory: cd eigent Install dependencies (Node.js 18-22 required): npm install Start the app in development mode (connects to cloud services): npm run dev
- Where can I get eigent?
- The source code and installation instructions are on GitHub: https://github.com/eigent-ai/eigent
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Fair-code workflow automation platform for building AI agents and workflows, combining a visual canvas with custom code and 1500+ integrations.
Open-source SDK for building and running AI agents in Python and TypeScript, with tools, MCP, memory, and model portability.
Self-hosted auth gateway that lets AI agents call 1,000+ SaaS providers through SDK, CLI, MCP, HTTP, and OpenAPI without handing over credentials.
Self-hosted, open source AI assistant and persistent bot platform where you choose the model and sandbox, on web, desktop, iPhone and Android.
Open-source, local-first 3D building editor built on React Three Fiber and WebGPU, usable in the browser or from a CLI with MCP tools for AI agents.