隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
Eigent addresses the need for a fully open-source, locally deployable AI coworking platform that avoids cloud dependency and data privacy concerns. It solves the complexity of orchestrating multiple AI agents by providing a user-friendly desktop interface with parallel execution, customization, and enterprise features, unlike closed-source alternatives that lock users into proprietary ecosystems.
部署现实
当前可用的安装信号是：git clone https://github.com/eigent-ai/eigent.git && cd eigent && npm install && npm run dev。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 Apache-2.0。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build sophisticated multi-agent workflows that automate complex tasks, such as software development pipelines, data analysis, and business process automation. The platform supports single-agent harnesses for focused tasks, MCP integration for external tool connectivity, and built-in browser/terminal toolkits, enabling real-world applications like automated code review, report generation, and customer support automation. With enterprise features like SSO and access control, it can scale to organizational deployments, and its model-agnostic design allows integration with any LLM, making it highly versatile for custom AI solutions.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
eigent-ai/eigent 被追踪为 TypeScript 项目，主要属于 AI Agent, Automation 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 15k Star，今日 +33，本周 +0，本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 64 天，未关闭 Issue 为 208，约占总 Star 的 1.39%。这只是采用信号，不替代工程尽调。
采用检查：1.8k Fork 和 15k Watcher 反映项目被复用和关注的程度。许可证信号：Apache-2.0。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「TypeScript 技术栈团队评估生态原生工具」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 33。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 Apache-2.0，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
15k 星标
复用
1.8k 复刻
关注
15k 关注者
维护
moderate
许可证
Apache-2.0
未解决 Issue
208
Eigent is an open-source desktop application for building, managing, and deploying custom AI workforces. It enables users to automate complex workflows through multi-agent coordination, local deployment, and integration with various models and tools.
核心特性
- Multi-Agent Coordination: Handle complex multi-agent workflows with parallel execution. - Local Deployment: Run fully standalone with complete control over data. - Model Agnostic: Support any model of your choice, including local inference and cloud APIs.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
Automation
Workflow automation, integration glue, and orchestration
git clone https://github.com/eigent-ai/eigent.git && cd eigent && npm install && npm run dev70
健康评分
一般
提交活跃度
Jul 29, 2025
创建于
Aug 11, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
eigent-ai
GitHub 主页obra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
n8n-io/n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
Eigent addresses the need for a fully open-source, locally deployable AI coworking platform that avoids cloud dependency and data privacy concerns. It solves the complexity of orchestrating multiple AI agents by providing a user-friendly desktop interface with parallel execution, customization, and enterprise features, unlike closed-source alternatives that lock users into proprietary ecosystems.
能力范围
Developers can build sophisticated multi-agent workflows that automate complex tasks, such as software development pipelines, data analysis, and business process automation. The platform supports single-agent harnesses for focused tasks, MCP integration for external tool connectivity, and built-in browser/terminal toolkits, enabling real-world applications like automated code review, report generation, and customer support automation. With enterprise features like SSO and access control, it can scale to organizational deployments, and its model-agnostic design allows integration with any LLM, making it highly versatile for custom AI solutions.
结论
Eigent is ideal for developers and organizations seeking a transparent, self-hosted AI agent platform with multi-agent orchestration and strong privacy controls. Those who prefer fully managed cloud services or lack the technical resources for local deployment may find the setup challenging. The key trade-off is between data sovereignty and customization versus the convenience of cloud-based alternatives.