{"id":18315776,"url":"https://github.com/aiplanethub/openagi","last_synced_at":"2026-01-18T08:23:12.680Z","repository":{"id":231659446,"uuid":"781844208","full_name":"aiplanethub/openagi","owner":"aiplanethub","description":"Paving the way for open agents and AGI for all.","archived":false,"fork":false,"pushed_at":"2025-02-25T11:22:33.000Z","size":5728,"stargazers_count":332,"open_issues_count":9,"forks_count":75,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-10-27T08:53:47.127Z","etag":null,"topics":["agents","agi","generative-ai","hacktoberfest","hacktoberfest-accepted","hacktoberfest2023","hacktoberfest2024","large-language-models","llm","openagi","openai"],"latest_commit_sha":null,"homepage":"https://openagi.aiplanet.com/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aiplanethub.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":null,"code_of_conduct":"CODE_OF_CONDUCT.md","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":"2024-04-04T06:33:47.000Z","updated_at":"2025-09-26T08:56:25.000Z","dependencies_parsed_at":"2024-04-05T07:24:07.179Z","dependency_job_id":"b7d87e4c-433a-41ca-ab60-5e2b146292b4","html_url":"https://github.com/aiplanethub/openagi","commit_stats":null,"previous_names":["aiplanethub/openagi"],"tags_count":21,"template":false,"template_full_name":null,"purl":"pkg:github/aiplanethub/openagi","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aiplanethub%2Fopenagi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aiplanethub%2Fopenagi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aiplanethub%2Fopenagi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aiplanethub%2Fopenagi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aiplanethub","download_url":"https://codeload.github.com/aiplanethub/openagi/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aiplanethub%2Fopenagi/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28534143,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-18T00:39:45.795Z","status":"online","status_checked_at":"2026-01-18T02:00:07.578Z","response_time":98,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["agents","agi","generative-ai","hacktoberfest","hacktoberfest-accepted","hacktoberfest2023","hacktoberfest2024","large-language-models","llm","openagi","openai"],"created_at":"2024-11-05T17:01:07.645Z","updated_at":"2026-01-18T08:23:12.659Z","avatar_url":"https://github.com/aiplanethub.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003ch1 align=\"center\"\u003eOpenAGI \u003c/h1\u003e\n\u003cimg src=\"https://github.com/aiplanethub/openagi/blob/dev/assets/openagi.png\"\u003e\n\u003ch2 align=\"center\"\u003eMaking the development of autonomous human-like agents accessible to all\u003c/h2\u003e\n\n\u003ca href=\"https://img.shields.io/badge/Python-3.9%20%7C%203.10%20%7C%203.11-3776AB.svg?style=flat\u0026logo=python\u0026logoColor=white\"\u003e\u003cimg src=\"https://img.shields.io/badge/Python-3.9%20%7C%203.10%20%7C%203.11-3776AB.svg?style=flat\u0026logo=python\u0026logoColor=white\" alt=\"Python Versions\"\u003e\u003c/a\u003e\n\u003ca href=\"https://pypi.org/project/openagi/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/openagi.svg?style=flat\u0026logo=pypi\u0026logoColor=white\" alt=\"PyPI version\"\u003e\u003c/a\u003e\n\u003ca href=\"https://discord.gg/4aWV7He2QU\"\u003e\u003cimg src=\"https://dcbadge.vercel.app/api/server/4aWV7He2QU?style=flat\" alt=\"Discord\" /\u003e\u003c/a\u003e\n\u003ca href=\"https://twitter.com/aiplanethub\"\u003e\u003cimg src=\"https://img.shields.io/twitter/follow/aiplanethub\" alt=\"Twitter\" /\u003e\u003c/a\u003e\n\u003ca href=\"https://medium.aiplanet.com\"\u003e\u003cimg src=\"https://img.shields.io/badge/Medium-Blog-black?style=flat\u0026logo=medium\" alt=\"Medium Blog\" /\u003e\u003c/a\u003e\n\n\u003cp\u003eOpenAGI aims to make human-like agents accessible to everyone, thereby paving the way towards open agents and, eventually, AGI for everyone. We strongly believe in the transformative power of AI and are confident that this initiative will significantly contribute to solving many real-life problems. Currently, OpenAGI is designed to offer developers a framework for creating autonomous human-like agents.\u003c/p\u003e\n\u003ci\u003e\u003ca href=\"https://discord.gg/4aWV7He2QU\"\u003e👉 Join our Discord community!\u003c/a\u003e\u003c/i\u003e\n\u003c/div\u003e\n\n## Installation\n\n1. Setup a virtual environment.\n\n```bash\n# For Mac and Linux users\npython3 -m venv venv\nsource venv/bin/activate\n\n# For Windows users\npython -m venv venv\nvenv/scripts/activate\n```\n\n2. Install the openagi\n\n```bash\npip install openagi\n```\n\nor \n```\ngit clone https://github.com/aiplanethub/openagi.git\npip install -e .\n```\n\n## Example (Manual Agent Execution)\n\nWorkers are used to create a Multi-Agent architecture.\n\nFollow this example to create a **Trip Planner Agent** that helps you plan the itinerary to SF. \n\n```py\nfrom openagi.agent import Admin\nfrom openagi.planner.task_decomposer import TaskPlanner\nfrom openagi.actions.tools.ddg_search import DuckDuckGoSearch\nfrom openagi.llms.openai import OpenAIModel\nfrom openagi.worker import Worker\n\nplan = TaskPlanner(human_intervene=False)\naction = DuckDuckGoSearch\n\nimport os\nos.environ['OPENAI_API_KEY'] = \"sk-xxxx\"\nconfig = OpenAIModel.load_from_env_config()\nllm = OpenAIModel(config=config)\n\ntrip_plan = Worker(\n        role=\"Trip Planner\",\n        instructions=\"\"\"\n        User loves calm places, suggest the best itinerary accordingly.\n        \"\"\",\n        actions=[action],\n        max_iterations=10)\n\nadmin = Admin(\n    llm=llm,\n    actions=[action],\n    planner=plan,\n)\nadmin.assign_workers([trip_plan])\n\nres = admin.run(\n    query=\"Give me total 3 Days Trip to San francisco Bay area\",\n    description=\"You are a knowledgeable local guide with extensive information about the city, it's attractions and customs\",\n)\nprint(res)\n```\n\n## Example (Autonomous Multi-Agent Execution)\n\nLets build a **Sports Agent** now that can run autonomously without any Workers.\n\n```py\nfrom openagi.planner.task_decomposer import TaskPlanner\nfrom openagi.actions.tools.tavilyqasearch import TavilyWebSearchQA\nfrom openagi.agent import Admin\nfrom openagi.llms.gemini import GeminiModel\n\nimport os\nos.environ['TAVILY_API_KEY'] = \"\u003creplace with Tavily key\u003e\"\nos.environ['GOOGLE_API_KEY'] = \"\u003creplace with Gemini key\u003e\"\nos.environ['Gemini_MODEL'] = \"gemini-1.5-flash\"\nos.environ['Gemini_TEMP'] = \"0.1\"\n\ngemini_config = GeminiModel.load_from_env_config()\nllm = GeminiModel(config=gemini_config)\n\n# define the planner\nplan = TaskPlanner(autonomous=True,human_intervene=True)\n\nadmin = Admin(\n    actions = [TavilyWebSearchQA],\n    planner = plan,\n    llm = llm,\n)\nres = admin.run(\n    query=\"I need cricket updates from India vs Sri lanka 2024 ODI match in Sri Lanka\",\n    description=f\"give me the results of India vs Sri Lanka ODI and respective Man of the Match\",\n)\nprint(res)\n``` \n\n## Long Term Memory like never before\n\nWith LTM, OpenAGI agents can now:\n\n- Recall past interactions to provide continuity in conversations.\n- Learn and adapt based on user inputs over time.\n- Deliver contextually relevant responses by referencing previous conversations.\n- Improve their accuracy and efficiency with each successive interaction.\n\n```py\nimport os\nfrom openagi.agent import Admin\nfrom openagi.llms.openai import OpenAIModel\nfrom openagi.memory import Memory\nfrom openagi.planner.task_decomposer import TaskPlanner\nfrom openagi.worker import Worker\nfrom openagi.actions.tools.ddg_search import DuckDuckGoSearch\n\nmemory = Memory(long_term=True)\n\nos.environ['OPENAI_API_KEY'] = \"-\"\nconfig = OpenAIModel.load_from_env_config()\nllm = OpenAIModel(config=config)\n\nweb_searcher = Worker(\n    role=\"Web Researcher\",\n    instructions=\"\"\"\n    You are tasked with conducting web searches using DuckDuckGo.\n    Find the most relevant and accurate information based on the user's query.\n    \"\"\",\n    actions=[DuckDuckGoSearch], \n)\n\nadmin = Admin(\n    actions=[DuckDuckGoSearch],\n    planner=TaskPlanner(human_intervene=False),\n    memory=memory,\n    llm=llm,\n)\nadmin.assign_workers([web_searcher])\n\nquery = input(\"Enter your search query: \")\ndescription = f\"Find accurate and relevant information for the query: {query}\"\n\nres = admin.run(query=query,description=description)\nprint(res)\n```\n\n## Documentation\n\nFor more queries find documentation for OpenAGI at [openagi.aiplanet.com](https://openagi.aiplanet.com/)\n\n## Use Cases:\n\n- **Education:** In education, agents can provide personalized learning experiences. They adapt and tailor learning content based on student's progress, performance and interests. It can extend to automating various other administrative tasks and assist teachers in improving their productivity.\n- **Finance and Banking:** Financial services can use agents for fraud detection, risk assessment, personalized banking advice, automating trading, and customer service. They help in analyzing large volumes of transactions to identify suspicious activities and offer tailored investment advice.\n- **Healthcare:** Agents can be deployed to monitor patients, provide personalized health recommendations, manage patient data, and automate administrative tasks. They can also assist in diagnosing diseases based on symptoms and medical history.\n\n## Get in Touch\n\nFor any queries/suggestions/support connect us at [openagi@aiplanet.com](mailto:openagi@aiplanet.com)\n\n## Contribution guidelines\n\nOpenAGI thrives in the rapidly evolving landscape of open-source projects. We wholeheartedly welcome contributions in various capacities, be it through innovative features, enhanced infrastructure, or refined documentation.\n\nFor a comprehensive guide on the contribution process, please click [here](https://github.com/aiplanethub/openagi/blob/main/CONTRIBUTING.md).\n\n## Support\n\n📚 [Documentation](https://openagi.aiplanet.com/)\n💬 [Discord Community](https://discord.gg/4aWV7He2QU)\n📝 [Issue Tracker](https://github.com/aiplanethub/openagi/issues)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faiplanethub%2Fopenagi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faiplanethub%2Fopenagi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faiplanethub%2Fopenagi/lists"}