本质:一个开源的Claude Cowork替代品
Eigent: An open source Claude Cowork alternative

原始链接: https://github.com/eigent-ai/eigent

## Eigent:你的开源AI劳动力 Eigent 是一款桌面应用程序,允许用户构建和部署定制的AI“劳动力”,以自动化复杂任务。它基于开源的CAMEL-AI框架构建,利用多智能体系统进行并行处理,并通过本地部署优先考虑数据隐私。 主要功能包括用户友好的界面,无需任何设置,协调多个AI智能体(如开发者、搜索者和文档创建者),以及通过模型上下文协议(MCP)支持自定义模型和集成——包括网络浏览、代码执行以及与Slack和Google Suite等流行平台的集成。 Eigent是完全开源的,提供透明度和社区贡献。它可以本地运行以实现完全的数据控制,也可以通过托管云平台运行。提供SSO和定制开发等企业级功能。该系统动态分解任务,利用专门的智能体并在需要时请求人工输入,例如行程规划、财务报表生成和市场分析。

Hacker News 新闻 | 过去 | 评论 | 提问 | 展示 | 招聘 | 提交 登录 Eigent:一个开源的Claude Cowork替代方案 (github.com/eigent-ai) 7 分,WorldPeas 发表于 1 小时前 | 隐藏 | 过去 | 收藏 | 2 条评论 keyle 发表于 10 分钟前 | 下一个 [–] “开源”具体指什么?是TypeScript客户端吗?因为它似乎只是通过$B apis进行连接,并提供一些积分和定价页面。我觉得我们对“开源”标签的使用范围有点太宽泛了,与实际提供的产品不符…… g5000 发表于 22 分钟前 | 上一个 [–] 有人试过这个吗?可能由于API成本,使用Opus在这种情况下没有意义,但其他模型或许可以很好地工作? 指南 | 常见问题 | 列表 | API | 安全 | 法律 | 申请YC | 联系 搜索:
相关文章

原文

Eigent is the open source cowork desktop application, empowering you to build, manage, and deploy a custom AI workforce that can turn your most complex workflows into automated tasks.

Built on CAMEL-AI's acclaimed open-source project, our system introduces a Multi-Agent Workforce that boosts productivity through parallel execution, customization, and privacy protection.

⭐ 100% Open Source - 🥇 Local Deployment - 🏆 MCP Integration

  • Zero Setup - No technical configuration required
  • Multi-Agent Coordination - Handle complex multi-agent workflows
  • Enterprise Feature - SSO/Access control
  • Local Deployment
  • Open Source
  • Custom Model Support
  • MCP Integration

Table of contents


🔓 Build in Public — Eigent is 100% open source from day one. Every feature, every commit, every decision is transparent. We believe the best AI tools should be built openly with the community, not behind closed doors.

🏠 Local Deployment (Recommended)

The recommended way to run Eigent — fully standalone with complete control over your data, no cloud account required.

👉 Full Local Deployment Guide

This setup includes:

  • Local backend server with full API
  • Local model integration (vLLM, Ollama, LM Studio, etc.)
  • Complete isolation from cloud services
  • Zero external dependencies

⚡ Quick Start (Cloud-Connected)

For a quick preview using our cloud backend — get started in seconds:

  • Node.js (version 18-22) and npm
git clone https://github.com/eigent-ai/eigent.git
cd eigent
npm install
npm run dev

Note: This mode connects to Eigent cloud services and requires account registration. For a fully standalone experience, use Local Deployment instead.

For organizations requiring maximum security, customization, and control:

  • Exclusive Features (like SSO & custom development)
  • Scalable Enterprise Deployment
  • Negotiated SLAs & implementation services

📧 For further details, please contact us at [email protected].

For teams who prefer managed infrastructure, we also offer a cloud platform. The fastest way to experience Eigent's multi-agent AI capabilities without setup complexity. We'll host the models, APIs, and cloud storage, ensuring Eigent runs flawlessly.

  • Instant Access - Start building multi-agent workflows in minutes.
  • Managed Infrastructure - We handle scaling, updates, and maintenance.
  • Premium Support - Subscribe and get priority assistance from our engineering team.

image-public-beta

Unlock the full potential of exceptional productivity with Eigent’s powerful features—built for seamless integration, smarter task execution, and boundless automation.

Employs a team of specialized AI agents that collaborate to solve complex tasks. Eigent dynamically breaks down tasks and activates multiple agents to work in parallel.

Eigent pre-defined the following agent workers:

  • Developer Agent: Writes and executes code, runs terminal commands.
  • Search Agent: Searches the web and extracts content.
  • Document Agent: Creates and manages documents.
  • Multi-Modal Agent: Processes images and audio.

Workforce


🧠 Comprehensive Model Support

Deploy Eigent locally with your preferred models.

Model


🔌 MCP Tools Integration (MCP)

Eigent comes with massive built-in Model Context Protocol (MCP) tools (for web browsing, code execution, Notion, Google suite, Slack etc.), and also lets you install your own tools. Equip agents with exactly the right tools for your scenarios – even integrate internal APIs or custom functions – to enhance their capabilities.

MCP

If a task gets stuck or encounters uncertainty, Eigent will automatically request human input.

Human-in-the-loop

Eigent is completely open-sourced. You can download, inspect, and modify the code, ensuring transparency and fostering a community-driven ecosystem for multi-agent innovation.

Opensource


1. Palm Springs Tennis Trip Itinerary with Slack Summary Replay ▶️

Prompt: We are two tennis fans and want to go see the tennis tournament ...
We are two tennis fans and want to go see the tennis tournament in Palm Springs 2026. I live in SF - please prepare a detailed itinerary with flights, hotels, things to do for 3 days - around the time semifinal/finals are happening. We like hiking, vegan food and spas. Our budget is $5K. The itinerary should be a detailed timeline of time, activity, cost, other details and if applicable a link to buy tickets/make reservations etc. for the item. Some preferences .Spa access would be nice but not necessary. When you finish this task, please generate a html report about this trip; write a summary of this plan and send text summary and report html link to slack #tennis-trip-sf channel.

Prompt: Please help me prepare a Q2 financial statement based on my bank ...
Please help me prepare a Q2 financial statement based on my bank transfer record file bank_transacation.csv in my desktop to a html report with chart to investors how much we have spent.

Prompt: Analyze the UK healthcare industry to support the planning ...
Analyze the UK healthcare industry to support the planning of my next company. Provide a comprehensive market overview, including current trends, growth projections, and relevant regulations. Identify the top 5–10 major opportunities, gaps, or underserved segments within the market. Present all findings in a well-structured, professional HTML report. Then send a message to slack #eigentr-product-test channel when this task is done to align the report content with my teammates.

Prompt: We are a company that produces high-end electric skateboards ...
We are a company that produces high-end electric skateboards, and we are considering entering the German market. Please prepare a detailed market entry feasibility report for me. The report needs to cover the following aspects: 1. Market Size & Regulations: Research the market size, annual growth rate, key players, and market share for Personal Light Electric Vehicles (PLEVs) in Germany. Simultaneously, provide a detailed breakdown and summary of German laws and regulations concerning the use of electric skateboards on public roads, including certification requirements (such as ABE certification) and insurance policies. 2. Consumer Profile: Analyze the profile of potential German consumers, including their age, income level, primary usage scenarios (commuting, recreation), key purchasing decision drivers (price, performance, brand, design), and the channels they typically use to gather information (forums, social media, offline retail stores). 3. Channels & Distribution: Investigate Germany’s mainstream online electronics sales platforms (e.g., Amazon.de, MediaMarkt.de) and high-end sporting goods offline retail chains. List the top 5 potential online and offline distribution partners and find the contact information for their purchasing departments, if possible. 4. Costing & Pricing: Based on the product cost structure in my Product_Cost.csv file on my desktop, and taking into account German customs duties, Value Added Tax (VAT), logistics and warehousing costs, and potential marketing expenses, estimate a Manufacturer’s Suggested Retail Price (MSRP) and analyze its competitiveness in the market. 5. Comprehensive Report & Presentation: Summarize all research findings into an HTML report file. The content should include data charts, key findings, and a final market entry strategy recommendation (Recommended / Not Recommended / Recommended with Conditions).

Prompt: To support the launch of our new Workforce Multiagent product ...
To support the launch of our new Workforce Multiagent product, please run a thorough SEO audit on our official website (https://www.camel-ai.org/) and deliver a detailed optimization report with actionable recommendations.

Prompt: I have a folder named mydocs inside my Documents directory ...
I have a folder named mydocs inside my Documents directory. Please scan it and identify all files that are exact or near duplicates — including those with identical content, file size, or format (even if file names or extensions differ). List them clearly, grouped by similarity.

Prompt: Please add this signature image to the Signature Areas in the PDF ...
Please add this signature image to the Signature Areas in the PDF. You could install the CLI tool ‘tesseract’ (needed for reliable location of ‘Signature Areas’ via OCR) to help finish this task.

  • Framework: FastAPI
  • Package Manager: uv
  • Async Server: Uvicorn
  • Authentication: OAuth 2.0, Passlib.
  • Multi-agent framework: CAMEL
  • Framework: React
  • Desktop App Framework: Electron
  • Language: TypeScript
  • UI: Tailwind CSS, Radix UI, Lucide React, Framer Motion
  • State Management: Zustand
  • Flow Editor: React Flow

Important

Star Eigent, You will receive all release notifications from GitHub without any delay ~ ⭐️

Topics Issues Discord Channel
Context Engineering - Prompt caching
- System prompt optimize
- Toolkit docstring optimize
- Context compression
Join Discord →
Multi-modal Enhancement - More accurate image understanding when using browser
- Advanced video generation
Join Discord →
Multi-agent system - Workforce support fixed workflow
- Workforce support multi-round conversion
Join Discord →
Browser Toolkit - BrowseCamp integration
- Benchmark improvement
- Forbid repeated page visiting
- Automatic cache button clicking
Join Discord →
Document Toolkit - Support dynamic file editing Join Discord →
Terminal Toolkit - Benchmark improvement
- Terminal-Bench integration
Join Discord →
Environment & RL - Environment design
- Data-generation
- RL framework integration (VERL, TRL, OpenRLHF)
Join Discord →

We believe in building trust and embracing all forms of open-source collaborations. Your creative contributions help drive the innovation of Eigent. Explore our GitHub issues and projects to dive in and show us what you’ve got 🤝❤️ Contribution Guideline

Eigent is built on top of CAMEL-AI.org's research and infrastructures. Sponsoring CAMEL-AI.org will make Eigent better.

📄 Open Source License

This repository is licensed under the Apache License 2.0.

For more information please contact [email protected]

  • GitHub Issues: Report bugs, request features, and track development. Submit an issue

  • Discord: Get real-time support, chat with the community, and stay updated. Join us

  • X (Twitter): Follow for updates, AI insights, and key announcements. Follow us

  • WeChat Community: Scan the QR code below to add our WeChat assistant, and join our WeChat community group.

联系我们 contact @ memedata.com