[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-578":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":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},578,"OpenManus","FoundationAgents\u002FOpenManus","FoundationAgents","No fortress, purely open ground.  OpenManus is Coming.","https:\u002F\u002Fopenmanus.github.io\u002F",null,"Python",56519,9835,416,339,0,12,67,319,49,45,"MIT License",false,"main",true,[],"2026-06-12 02:00:15","\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Flogo.jpg\" width=\"200\"\u002F>\n\u003C\u002Fp>\n\nEnglish | [中文](README_zh.md) | [한국어](README_ko.md) | [日本語](README_ja.md)\n\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFoundationAgents\u002FOpenManus?style=social)](https:\u002F\u002Fgithub.com\u002FFoundationAgents\u002FOpenManus\u002Fstargazers)\n \n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)  \n[![Discord Follow](https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002FDYn29wFk9z?style=flat)](https:\u002F\u002Fdiscord.gg\u002FDYn29wFk9z)\n[![Demo](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDemo-Hugging%20Face-yellow)](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Flyh-917\u002FOpenManusDemo)\n[![DOI](https:\u002F\u002Fzenodo.org\u002Fbadge\u002FDOI\u002F10.5281\u002Fzenodo.15186407.svg)](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.15186407)\n\n# 👋 OpenManus\n\nManus is incredible, but OpenManus can achieve any idea without an *Invite Code* 🛫!\n\nOur team members [@Xinbin Liang](https:\u002F\u002Fgithub.com\u002Fmannaandpoem) and [@Jinyu Xiang](https:\u002F\u002Fgithub.com\u002FXiangJinyu) (core authors), along with [@Zhaoyang Yu](https:\u002F\u002Fgithub.com\u002FMoshiQAQ), [@Jiayi Zhang](https:\u002F\u002Fgithub.com\u002Fdidiforgithub), and [@Sirui Hong](https:\u002F\u002Fgithub.com\u002FstellaHSR), we are from [@MetaGPT](https:\u002F\u002Fgithub.com\u002Fgeekan\u002FMetaGPT). The prototype is launched within 3 hours and we are keeping building!\n\nIt's a simple implementation, so we welcome any suggestions, contributions, and feedback!\n\nEnjoy your own agent with OpenManus!\n\nWe're also excited to introduce [OpenManus-RL](https:\u002F\u002Fgithub.com\u002FOpenManus\u002FOpenManus-RL), an open-source project dedicated to reinforcement learning (RL)- based (such as GRPO) tuning methods for LLM agents, developed collaboratively by researchers from UIUC and OpenManus.\n\n## Project Demo\n\n\u003Cvideo src=\"https:\u002F\u002Fprivate-user-images.githubusercontent.com\u002F61239030\u002F420168772-6dcfd0d2-9142-45d9-b74e-d10aa75073c6.mp4?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.UuHQCgWYkh0OQq9qsUWqGsUbhG3i9jcZDAMeHjLt5T4\" data-canonical-src=\"https:\u002F\u002Fprivate-user-images.githubusercontent.com\u002F61239030\u002F420168772-6dcfd0d2-9142-45d9-b74e-d10aa75073c6.mp4?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.UuHQCgWYkh0OQq9qsUWqGsUbhG3i9jcZDAMeHjLt5T4\" controls=\"controls\" muted=\"muted\" class=\"d-block rounded-bottom-2 border-top width-fit\" style=\"max-height:640px; min-height: 200px\">\u003C\u002Fvideo>\n\n## Installation\n\nWe provide two installation methods. Method 2 (using uv) is recommended for faster installation and better dependency management.\n\n### Method 1: Using conda\n\n1. Create a new conda environment:\n\n```bash\nconda create -n open_manus python=3.12\nconda activate open_manus\n```\n\n2. Clone the repository:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FFoundationAgents\u002FOpenManus.git\ncd OpenManus\n```\n\n3. Install dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n### Method 2: Using uv (Recommended)\n\n1. Install uv (A fast Python package installer and resolver):\n\n```bash\ncurl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n```\n\n2. Clone the repository:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FFoundationAgents\u002FOpenManus.git\ncd OpenManus\n```\n\n3. Create a new virtual environment and activate it:\n\n```bash\nuv venv --python 3.12\nsource .venv\u002Fbin\u002Factivate  # On Unix\u002FmacOS\n# Or on Windows:\n# .venv\\Scripts\\activate\n```\n\n4. Install dependencies:\n\n```bash\nuv pip install -r requirements.txt\n```\n\n### Browser Automation Tool (Optional)\n```bash\nplaywright install\n```\n\n## Configuration\n\nOpenManus requires configuration for the LLM APIs it uses. Follow these steps to set up your configuration:\n\n1. Create a `config.toml` file in the `config` directory (you can copy from the example):\n\n```bash\ncp config\u002Fconfig.example.toml config\u002Fconfig.toml\n```\n\n2. Edit `config\u002Fconfig.toml` to add your API keys and customize settings:\n\n```toml\n# Global LLM configuration\n[llm]\nmodel = \"gpt-4o\"\nbase_url = \"https:\u002F\u002Fapi.openai.com\u002Fv1\"\napi_key = \"sk-...\"  # Replace with your actual API key\nmax_tokens = 4096\ntemperature = 0.0\n\n# Optional configuration for specific LLM models\n[llm.vision]\nmodel = \"gpt-4o\"\nbase_url = \"https:\u002F\u002Fapi.openai.com\u002Fv1\"\napi_key = \"sk-...\"  # Replace with your actual API key\n```\n\n## Quick Start\n\nOne line for run OpenManus:\n\n```bash\npython main.py\n```\n\nThen input your idea via terminal!\n\nFor MCP tool version, you can run:\n```bash\npython run_mcp.py\n```\n\nFor unstable multi-agent version, you also can run:\n\n```bash\npython run_flow.py\n```\n\n### Custom Adding Multiple Agents\n\nCurrently, besides the general OpenManus Agent, we have also integrated the DataAnalysis Agent, which is suitable for data analysis and data visualization tasks. You can add this agent to `run_flow` in `config.toml`.\n\n```toml\n# Optional configuration for run-flow\n[runflow]\nuse_data_analysis_agent = true     # Disabled by default, change to true to activate\n```\nIn addition, you need to install the relevant dependencies to ensure the agent runs properly: [Detailed Installation Guide](app\u002Ftool\u002Fchart_visualization\u002FREADME.md##Installation)\n\n## How to contribute\n\nWe welcome any friendly suggestions and helpful contributions! Just create issues or submit pull requests.\n\nOr contact @mannaandpoem via 📧email: mannaandpoem@gmail.com\n\n**Note**: Before submitting a pull request, please use the pre-commit tool to check your changes. Run `pre-commit run --all-files` to execute the checks.\n\n## Community Group\nJoin our networking group on Feishu and share your experience with other developers!\n\n\u003Cdiv align=\"center\" style=\"display: flex; gap: 20px;\">\n    \u003Cimg src=\"assets\u002Fcommunity_group.jpg\" alt=\"OpenManus 交流群\" width=\"300\" \u002F>\n\u003C\u002Fdiv>\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=FoundationAgents\u002FOpenManus&type=Date)](https:\u002F\u002Fstar-history.com\u002F#FoundationAgents\u002FOpenManus&Date)\n\n## Sponsors\nThanks to [PPIO](https:\u002F\u002Fppinfra.com\u002Fuser\u002Fregister?invited_by=OCPKCN&utm_source=github_openmanus&utm_medium=github_readme&utm_campaign=link) for computing source support.\n> PPIO: The most affordable and easily-integrated MaaS and GPU cloud solution.\n\n\n## Acknowledgement\n\nThanks to [anthropic-computer-use](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fanthropic-quickstarts\u002Ftree\u002Fmain\u002Fcomputer-use-demo), [browser-use](https:\u002F\u002Fgithub.com\u002Fbrowser-use\u002Fbrowser-use) and [crawl4ai](https:\u002F\u002Fgithub.com\u002Funclecode\u002Fcrawl4ai) for providing basic support for this project!\n\nAdditionally, we are grateful to [AAAJ](https:\u002F\u002Fgithub.com\u002Fmetauto-ai\u002Fagent-as-a-judge), [MetaGPT](https:\u002F\u002Fgithub.com\u002Fgeekan\u002FMetaGPT), [OpenHands](https:\u002F\u002Fgithub.com\u002FAll-Hands-AI\u002FOpenHands) and [SWE-agent](https:\u002F\u002Fgithub.com\u002FSWE-agent\u002FSWE-agent).\n\nWe also thank stepfun(阶跃星辰) for supporting our Hugging Face demo space.\n\nOpenManus is built by contributors from MetaGPT. Huge thanks to this agent community!\n\n## Cite\n```bibtex\n@misc{openmanus2025,\n  author = {Xinbin Liang and Jinyu Xiang and Zhaoyang Yu and Jiayi Zhang and Sirui Hong and Sheng Fan and Xiao Tang and Bang Liu and Yuyu Luo and Chenglin Wu},\n  title = {OpenManus: An open-source framework for building general AI agents},\n  year = {2025},\n  publisher = {Zenodo},\n  doi = {10.5281\u002Fzenodo.15186407},\n  url = {https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.15186407},\n}\n```\n","OpenManus 是一个无需邀请码即可使用的开源代理项目。它基于 Python 开发，核心功能是提供了一个简单易用的框架来创建和管理自己的代理应用，并且支持强化学习（如 GRPO）等高级调优方法。该项目强调开放性和可扩展性，适合那些希望快速构建个性化代理服务的研究人员、开发者以及企业使用。此外，OpenManus 还拥有活跃的社区支持与贡献机制，鼓励用户提出建议或直接参与代码改进。",2,"2026-06-11 02:37:44","top_all"]