[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73604":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":44,"readmeContent":45,"aiSummary":46,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":47,"discoverSource":48},73604,"eko","FellouAI\u002Feko","FellouAI","Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai","https:\u002F\u002Ffellou.ai\u002Feko",null,"TypeScript",4926,439,97,5,0,2,10,29.93,"MIT License",false,"main",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"agent","agentic-ai","agentic-ai-development","agentic-framework","agentic-workflow","agents","ai-agents","browser-automation","browseruse","chain-of-thought","computer-automation","computeruse","genai","llm-agents","llm-inference","llmapi","natural-language-inference","prompt-engineering","rag","workflow","2026-06-12 02:03:15","\n\n\n\u003Ch1 align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FFellouAI\u002Feko\" target=\"_blank\">\n    \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F55dbdd6c-2b08-4e5f-a841-8fea7c2a0b92\" alt=\"eko-logo\" width=\"200\" height=\"200\">\n  \u003C\u002Fa>\n  \u003Cbr>\n  \u003Csmall>Eko - Build Production-ready Agentic Workflow with Natural Language\u003C\u002Fsmall>\n\u003C\u002Fh1>\n\n\n\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg)](LICENSE) [![Build Status](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fbuild-passing-brightgreen.svg)](https:\u002F\u002Fexample.com\u002Fbuild-status) [![Version](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fpackage-json\u002Fv\u002FFellouAI\u002Feko?color=yellow)](https:\u002F\u002Feko.fellou.ai\u002Fdocs\u002Frelease\u002Fversions\u002F)\n\nEko (pronounced like 'echo') is a production-ready JavaScript framework that enables developers to create reliable agents, **from simple commands to complex workflows**. It provides a unified interface for running agents in both **computer and browser environments**.\n\n## News\n\n- **2025-11:** Eko 4.0 supports chat conversations & optimizes agent logic.\n- **2025-09:** Eko 3.0 introduces dependency-aware parallel agent execution.\n- **2025-09:** New pause, resume, and interrupt controls with `task_snapshot` workflow recovery.\n- **2025-09:** Monorepo tooling migrated to pnpm for consistent workspace management.\n\n## Upgrading to Eko 4.0\n\nFollow these steps when moving an existing Eko 3.x project to 4.0:\n\n1. Update dependencies with `pnpm up @eko-ai\u002Feko @eko-ai\u002Feko-nodejs @eko-ai\u002Feko-web @eko-ai\u002Feko-extension`.\n2. Regenerate saved workflows or exported plans so they use the v3 schema and dependency graph format.\n3. Clean and reinstall using pnpm (`rm -rf node_modules && pnpm install`), then rebuild any browser or desktop bundles.\n4. Re-run automated demos and update documentation to reflect the new pause\u002Finterrupt APIs and parallel agent behavior.\n\n\n## Framework Comparison\n\n| Feature                              | Eko   | Langchain  | Browser-use  | Dify.ai  | Coze   |\n|--------------------------------------|-------|------------|--------------|----------|--------|\n| **Supported Platform**               | **All platform**  | Server side  | Browser  | Web  | Web  |\n| **One sentence to multi-step workflow** | ✅    | ❌          | ✅            | ❌        | ❌      |\n| **Intervenability**                  | ✅    | ✅          | ❌            | ❌        | ❌      |\n| **Task Parallel** | ✅    | ❌          | ❌            | ❌        | ❌      |\n| **Development Efficiency**           | **High**  | Low      | Middle        | Middle    | Low    |\n| **Task Complexity**           | **High**  | High      | Low        | Middle    | Middle    | Middle       |\n| **Open-source**                      | ✅    | ✅          | ✅            | ✅        | ❌      |\n| **Access to private web resources** | ✅ | ❌          | ❌            | ❌        | ❌      |\n\n## Features\n\n- [x] Pure JavaScript: Built for browsers and Node.js.🚀\n- [x] Multi-Agent: Unleash power with multiple Agents in one task.📈\n- [x] Agent\u002FTool Flexibility: Customize new Agents and Tools in just one line.🎉\n- [x] Native MCP: Connects seamlessly with [Awesome MCP Servers](https:\u002F\u002Fmcpservers.org\u002F).🔗\n- [x] Dynamic LLM: Balance speed and performance with flexible model choices.⚙️\n- [x] Human-in-the-loop: Intervene when it matters most.🤝\n- [x] Stream Planning: Dynamic rendering made easy.🎨\n- [x] Loop & Listener Tasks: Automate any repetitive task.🤖\n- [ ] Observable Chain: *Coming soon*\n- [ ] Native A2A: *Coming soon*\n\n## Quickstart\n\n> **Note**: Please refer to the [Eko Quickstart guide](https:\u002F\u002Feko.fellou.ai\u002Fdocs\u002Fgetting-started\u002Fquickstart\u002F) guide for full instructions on how to run it.\n\n> **Security Warning**\n> \n> DO NOT use API Keys in browser\u002Ffrontend code!\n>\n> This will expose your credentials and may lead to unauthorized usage.\n>\n> Best Practices: Configure backend API proxy request through baseURL and request headers.\n>\n> Please refer to the link: https:\u002F\u002Feko.fellou.ai\u002Fdocs\u002Fgetting-started\u002Fconfiguration#web-environment\n\n```typescript\nconst llms: LLMs = {\n  default: {\n    provider: \"anthropic\",\n    model: \"claude-sonnet-4-5-20250929\",\n    apiKey: \"your-api-key\"\n  },\n  gemini: {\n    provider: \"google\",\n    model: \"gemini-2.5-pro\",\n    apiKey: \"your-api-key\"\n  },\n  openai: {\n    provider: \"openai\",\n    model: \"gpt-5\",\n    apiKey: \"your-api-key\"\n  },\n  \u002F\u002F OpenAI-compatible models (Qwen, Doubao, etc.)\n  qwen: {\n    provider: \"openai\",\n    model: \"qwen-plus\",\n    apiKey: \"your-qwen-api-key\",\n    config: {\n      baseURL: \"https:\u002F\u002Fdashscope-intl.aliyuncs.com\u002Fcompatible-mode\u002Fv1\"\n    }\n  },\n  doubao: {\n    provider: \"openai\",  \u002F\u002F Use OpenAI provider for compatibility\n    model: \"doubao-seed-1-6-250615\",  \u002F\u002F or other Doubao model\n    apiKey: \"your-volcengine-api-key\",\n    config: {\n      baseURL: \"https:\u002F\u002Fark.cn-beijing.volces.com\u002Fapi\u002Fv3\"  \u002F\u002F Volcengine endpoint\n    }\n  }\n\n};\n\nlet agents: Agent[] = [new BrowserAgent(), new FileAgent()];\nlet eko = new Eko({ llms, agents });\nlet result = await eko.run(\"Search for the latest news about Musk, summarize and save to the desktop as Musk.md\");\n```\n\n```bash\n$ pnpm install @eko-ai\u002Feko\n```\n\n## Example Projects\n\nThe repository ships with three workspace examples under the `example\u002F` folder.\n\n### Prerequisites\n\nBefore running any example, install dependencies and build the core packages from the root directory:\n\n```bash\npnpm install\npnpm build\n```\n\n### Browser Extension (`example\u002Fextension`)\n\n```bash\ncd example\u002Fextension\npnpm install\npnpm run build\n```\n\nLoad the generated `dist` directory via `chrome:\u002F\u002Fextensions` → Developer Mode → Load unpacked.\nConfigure your API key in the extension options before running the automation task.\n\n### Node.js Automation (`example\u002Fnodejs`)\n\n```bash\ncd example\u002Fnodejs\npnpm install\npnpm playwright install   # first time only, installs browsers\npnpm run build\nOPENAI_API_KEY=... ANTHROPIC_API_KEY=... pnpm run start\n```\n\nThe Node.js demo drives Playwright through Eko; provide at least one model API key before running it.\n\n### Web Login Demo (`example\u002Fweb`)\n\n```bash\ncd example\u002Fweb\npnpm install\npnpm run start\n```\n\nThis starts a React dev server on the default port with a simple login flow that you can automate\nwith the browser or web agents.\n\n## Use Cases\n\n- Browser automation and web scraping\n- System file and process management\n- Workflow automation\n- Data processing and organization\n- GUI automation\n- Multi-step task orchestration\n\n## Documentation\n\nVisit our [documentation site](https:\u002F\u002Feko.fellou.ai\u002Fdocs) for:\n\n- Getting started guide\n- API reference\n- Usage examples\n- Best practices\n- Configuration options\n\n## Development Environments\n\nEko can be used in multiple environments:\n\n- Browser Extension\n- Web Applications\n- Node.js Applications\n\n## Community and Support\n\n- Report issues on [GitHub Issues](https:\u002F\u002Fgithub.com\u002FFellouAI\u002Feko\u002Fissues)\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=FellouAI\u002Feko&type=Date)](https:\u002F\u002Fstar-history.com\u002F#FellouAI\u002Feko&Date)\n\n\n## License\n\nEko is released under the MIT License. See the [LICENSE](LICENSE) file for details.\n","Eko 是一个用于构建基于自然语言的生产级代理工作流的框架。它支持从简单的命令到复杂的工作流程，并且能够在计算机和浏览器环境中运行。Eko 的核心功能包括多代理并行执行、任务中断与恢复机制以及对私有网络资源的访问能力。这些特点使得 Eko 适合于需要高度定制化和自动化处理的任务场景，例如企业内部的流程自动化、数据处理或客户服务等。此外，Eko 提供了高效的开发体验，能够帮助开发者快速搭建和部署复杂的代理应用。","2026-06-11 03:46:22","high_star"]