eigent-ai/eigent

Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

What it solves

Eigent provides a desktop environment for building and managing a custom AI workforce. It allows users to automate complex, multi-step workflows by coordinating multiple specialized AI agents that can work in parallel, reducing the manual effort required for intricate digital tasks.

How it works

Built on the CAMEL-AI framework, Eigent operates as a desktop application (via Electron) that connects to various LLMs. It supports both single-agent tasks and multi-agent coordination. Users can deploy it locally for full data privacy or connect to a cloud backend. The system integrates with the Model Context Protocol (MCP) and includes built-in toolkits for browser and terminal access, enabling agents to interact with the user's machine and the web.

Who it’s for

It is designed for developers and power users who want to automate desktop-based workflows, such as generating reports from GitHub PRs, organizing local files, or building software projects through parallel agent execution.

Highlights

  • Multi-Agent Workforce: Ability to deploy multiple specialized agents to divide and conquer complex tasks.
  • Local-First Deployment: Supports local model integration (vLLM, Ollama, LM Studio) for complete data isolation.
  • Model Agnostic: Works with cloud APIs, enterprise gateways, or local inference engines.
  • Integrated Toolkits: Includes built-in browser and terminal tools for direct system interaction.
  • Automation: Supports scheduling recurring workflows to run autonomously.

Related

  • Project
    Agenta-AI/agenta

    An open-source workspace for building and running AI agents that can automate work through interactive chat or scheduled background tasks.

  • Project
    omnigent-ai/omnigent

    Omnigent is an open‑source meta‑harness that unifies many LLM coding agents (Claude Code, Codex, Cursor, etc.) under one CLI and web UI, letting you run, combine, and govern them across devices and cloud sandboxes, with built‑in collaboration and policy features.

  • Project
    hAcKlyc/MyAgents

    An open-source desktop workspace for personal AI agents that integrates local files, terminals, and a task scheduling system to move beyond simple chat interfaces.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    rush86999/atom

    An open-source, self-hosted AI agent workforce platform that uses a maturity model and outcome verification to transition agents from supervised to autonomous business automation.