{"id":13486905,"url":"https://github.com/agiresearch/OpenAGI","last_synced_at":"2025-03-27T21:31:41.870Z","repository":{"id":152513943,"uuid":"625084397","full_name":"agiresearch/OpenAGI","owner":"agiresearch","description":"OpenAGI: When LLM Meets Domain Experts","archived":false,"fork":false,"pushed_at":"2024-09-02T19:40:36.000Z","size":345814,"stargazers_count":1946,"open_issues_count":5,"forks_count":162,"subscribers_count":28,"default_branch":"main","last_synced_at":"2024-10-29T15:05:25.821Z","etag":null,"topics":["agi","llm","opensource"],"latest_commit_sha":null,"homepage":"http://aios.foundation","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/agiresearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-04-08T02:58:55.000Z","updated_at":"2024-10-29T09:00:05.000Z","dependencies_parsed_at":"2023-10-16T13:08:31.531Z","dependency_job_id":"6fb0cb5a-e467-434a-8898-1993ba74c2d3","html_url":"https://github.com/agiresearch/OpenAGI","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agiresearch%2FOpenAGI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agiresearch%2FOpenAGI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agiresearch%2FOpenAGI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agiresearch%2FOpenAGI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agiresearch","download_url":"https://codeload.github.com/agiresearch/OpenAGI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222321713,"owners_count":16966432,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agi","llm","opensource"],"created_at":"2024-07-31T18:00:52.773Z","updated_at":"2025-03-27T21:31:41.850Z","avatar_url":"https://github.com/agiresearch.png","language":"Python","funding_links":[],"categories":["[↑](#table-of-contents) Code|Apps|Tools","[OpenAGI](https://github.com/agiresearch/OpenAGI)","Other useful resources","其他资源","Uncategorized","Frameworks and Platforms","Miscellaneous","Platforms/API","Agentic Framework","Learning","Python","Agentic Frameworks","Agent Integration \u0026 Deployment Tools","排行榜 [2025-03-18]","Agentic Systems"],"sub_categories":["Links","LLM 评估工具","Uncategorized","Advanced Components","Repositories","AI Developer Toolkit"],"readme":"# OpenAGI: Package for AI Agent Creation\n\u003ca href='https://arxiv.org/abs/2304.04370'\u003e\u003cimg src='https://img.shields.io/badge/Paper-PDF-red'\u003e\u003c/a\u003e\n[![Code License](https://img.shields.io/badge/Code%20License-MIT-green.svg)](https://github.com/agiresearch/OpenAGI/blob/main/LICENSE)\n\u003ca href='https://discord.gg/B2HFxEgTJX'\u003e\u003cimg src='https://img.shields.io/badge/Community-Discord-8A2BE2'\u003e\u003c/a\u003e\n\n\n## ✈️ Getting Started\nOpenAGI is used as the agent creation package to build agents for [AIOS](https://github.com/agiresearch/AIOS).\n**Notice:** For building up agents in the AIOS, please migrate to the [Cerebrum](https://github.com/agiresearch/Cerebrum), which is our latest SDK to connect with AIOS kernel.\n\n### Installation\nFrom PyPI\n```\npip install pyopenagi\n```\nLocally\n```\ngit clone https://agiresearch/OpenAGI\ncd OpenAGI\npip install -e .\n```\n\n### Usage\n\n#### Add a new agent\nTo add a new agent, first you need to create a folder under the pyopenagi/agents folder.\nThe folder needs to be the following structure:\n```\n- pyopenagi/agents\n  - author\n    - agent_name\n      - agent.py # main code for the agent execution logic\n      - config.json # set up configurations for agent\n      - meta_requirements.txt # dependencies that the agent needs\n```\nIf you want to use external tools provided by openagi in your agents, you can follow instructions of setting up tools in [How to setup external tools](./tools.md).\nIf you want to add new tools for your developing agent,\nyou need to add a new tool file in the [folder](./pyopenagi/tools/).\n\n#### Upload agent\nIf you have developed and tested your agent, and you would like to share your agents, you can use the following to upload your agents\n```\npython pyopenagi/agents/interact.py --mode upload --agent \u003cauthor_name/agent_name\u003e\n```\n💡Note that the `agent` param must exactly match the folder you put your agent locally.\n\n#### Download agent\nIf you want to look at implementations of other agents that others have developed, you can use the following command:\n```\npython pyopenagi/agents/interact.py --mode download --agent \u003cauthor_name/agent_name\u003e\n```\n\n## 🚀 Contributions\n\nFor detailed information on how to contribute, see [CONTRIBUTE](./CONTRIBUTE.md). If you would like to contribute to the codebase, [issues](https://github.com/agiresearch/OpenAGI/issues) or [pull requests](https://github.com/agiresearch/OpenAGI/pulls) are always welcome!\n\n## 🖋️ Research\nPlease check out our [implementation](https://github.com/agiresearch/OpenAGI/tree/research) for our research paper [OpenAGI: When LLM Meets Domain Experts](https://arxiv.org/abs/2304.04370).\n\n```\n@article{openagi,\n  title={OpenAGI: When LLM Meets Domain Experts},\n  author={Ge, Yingqiang and Hua, Wenyue and Mei, Kai and Ji, Jianchao and Tan, Juntao and Xu, Shuyuan and Li, Zelong and Zhang, Yongfeng},\n  journal={In Advances in Neural Information Processing Systems (NeurIPS)},\n  year={2023}\n}\n```\n\n## 🌍 OpenAGI Contributors\n[![OpenAGI contributors](https://contrib.rocks/image?repo=agiresearch/OpenAGI\u0026max=300)](https://github.com/agiresearch/OpenAGI/graphs/contributors)\n\n\n\n## 🌟 Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=agiresearch/OpenAGI\u0026type=Date)](https://star-history.com/#agiresearch/OpenAGI\u0026Date)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagiresearch%2FOpenAGI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagiresearch%2FOpenAGI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagiresearch%2FOpenAGI/lists"}