{"id":26586193,"url":"https://i-am-bee.github.io/beeai-framework/","last_synced_at":"2025-03-23T11:02:21.108Z","repository":{"id":254489366,"uuid":"846579774","full_name":"i-am-bee/beeai-framework","owner":"i-am-bee","description":"Build production-ready AI agents in both Python and Typescript","archived":false,"fork":false,"pushed_at":"2025-03-19T16:15:56.000Z","size":5212,"stargazers_count":2075,"open_issues_count":45,"forks_count":243,"subscribers_count":36,"default_branch":"main","last_synced_at":"2025-03-19T16:38:40.237Z","etag":null,"topics":["agents","ai","ai-agent","framework","llm","multiagent","python","typescript"],"latest_commit_sha":null,"homepage":"https://i-am-bee.github.io/beeai-framework/","language":"TypeScript","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/i-am-bee.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-23T14:03:06.000Z","updated_at":"2025-03-19T16:23:11.000Z","dependencies_parsed_at":"2024-11-04T13:18:32.947Z","dependency_job_id":"49259fe9-551e-4935-b027-1273fa8b684c","html_url":"https://github.com/i-am-bee/beeai-framework","commit_stats":{"total_commits":433,"total_committers":23,"mean_commits":18.82608695652174,"dds":"0.17551963048498842","last_synced_commit":"a5d1b02e0296f472664d72719e17f2137a9bd1e4"},"previous_names":["i-am-bee/bee-agent-framework","i-am-bee/beeai-framework"],"tags_count":75,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i-am-bee%2Fbeeai-framework","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i-am-bee%2Fbeeai-framework/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i-am-bee%2Fbeeai-framework/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i-am-bee%2Fbeeai-framework/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/i-am-bee","download_url":"https://codeload.github.com/i-am-bee/beeai-framework/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244560374,"owners_count":20472219,"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":["agents","ai","ai-agent","framework","llm","multiagent","python","typescript"],"created_at":"2025-03-23T11:01:42.094Z","updated_at":"2025-03-23T11:02:21.086Z","avatar_url":"https://github.com/i-am-bee.png","language":"TypeScript","funding_links":[],"categories":["Agentic AI"],"sub_categories":[],"readme":"\n\u003ch1 align=\"left\"\u003eBeeAI Framework \u003c/h1\u003e\n\n\u003cdiv align=\"left\"\u003e\n\n[![Python library](https://img.shields.io/badge/Python-4584b6?style=flat\u0026logo=python\u0026logoColor=white)](https://github.com/i-am-bee/beeai-framework/tree/main/python)\n[![Typescript library](https://img.shields.io/badge/TypeScript-3178c6?style=flat\u0026logo=typescript\u0026logoColor=white)](https://github.com/i-am-bee/beeai-framework/tree/main/typescript)\n[![License](https://img.shields.io/badge/License-Apache%202.0-EA7826?style=flat)](https://github.com/i-am-bee/beeai-framework?tab=Apache-2.0-1-ov-file#readme)\n[![Bluesky](https://img.shields.io/badge/Bluesky-0285FF?style=flat\u0026logo=bluesky\u0026logoColor=white)](https://bsky.app/profile/beeaiagents.bsky.social)\n[![Discord](https://img.shields.io/discord/1309202615556378705?style=social\u0026logo=discord\u0026logoColor=black\u0026label=Discord\u0026labelColor=7289da\u0026color=black)](https://discord.com/invite/NradeA6ZNF)\n[![GitHub Repo stars](https://img.shields.io/github/stars/I-am-bee/beeai-framework)](https://github.com/i-am-bee/beeai-framework)\n\n\u003c/div\u003e\n\nBuild production-ready multi-agent systems in [Python](/python) or [TypeScript](/typescript).\n\n## Latest updates 🚀\n\n| Date       | Language      | Update Description                                                                 \n|------------|---------------|-------------------------------------------------------------------------------------|\n| 2025/02/19 | Python        | Launched Python library alpha. See [getting started guide](#installation).               |\n| 2025/02/07 | TypeScript    | Introduced [Backend](/typescript/docs/backend.md) module to simplify working with AI services (chat, embedding). See [migration guide](/typescript/docs/migration_guide.md). |\n| 2025/01/28 | TypeScript    | Added support for DeepSeek R1, check out the [Competitive Analysis Workflow example](/typescript/examples/workflows/competitive-analysis). |\n| 2025/01/09 | TypeScript    | Introduced [Workflows](/typescript/docs/workflows.md), a way of building multi-agent systems. Added support for [Model Context Protocol](/typescript/docs/tools.md#using-the-mcptool-class). |\n| 2024/12/09 | TypeScript    | Added support for LLaMa 3.3. See [multi-agent workflow example using watsonx](/typescript/examples/workflows/multiAgents.ts) or explore [other available providers](/typescript/docs/backend.md#providers-implementations).        |\n| 2024/11/21 | TypeScript    | Added an experimental [Streamlit agent](/typescript/examples/agents/experimental/streamlit.ts). |\n\n\nFor a full changelog, see our [releases page](https://github.com/i-am-bee/beeai-framework/releases).\n\n---\n\n## Why BeeAI?\n\n**🏆 Build for your use case.**  Implement simple to complex multi-agent patterns using [Workflows](/python/docs/workflows.md), start with a [ReActAgent](/python/examples/agents/react.py), or easily [build your own agent architecture](/python/docs/agents.md#creating-your-own-agent). There is no one-size-fits-all agent architecture, you need full flexibility in orchestrating agents and defining their roles and behaviors. \n\n**🔌 Seamlessly integrate with your models and tools.** Get started with any model from [Ollama](/python/examples/backend/providers/ollama.py), [Groq](/python/examples/backend/providers/groq.py), [OpenAI](/python/examples/backend/providers/openai_example.py), [watsonx.ai](/python/examples/backend/providers/watsonx.py), and [more](/python/docs/backend.md#supported-providers). Leverage tools from [LangChain](/python/examples/tools/langchain.py), connect to any server using the [Model Context Protocol](/python/docs/tools.md#mcp-tool), or build your own [custom tools](/python/docs/tools.md#creating-custom-tools). BeeAI is designed to integrate with the systems and capabilities you need.\n\n**🚀 Scale with production-grade controls.** Optimize token usage through configurable [memory strategies](/python/docs/memory.md), persist and restore agent state via [(de)serialization](/python/docs/serialization.md), generate structured outputs, and execute generated code in a sandboxed environment (coming soon). When things go wrong, the [emitter](/python/docs/emitter.md) system tracks the full agent workflow, generating detailed [events](/python/docs/events.md) for monitoring and analysis. [Telemetry](/python/docs/instrumentation.md) and [logging](/python/docs/logger.md) capabilities capture key diagnostic data. When issues arise, BeeAI handles [errors](/python/docs/errors.md) gracefully with clear, well-defined exceptions.\n\n---\n\n## Installation\n\nTo install the Python library:\n```shell\npip install beeai-framework\n```\n\nTo install the TypeScript library:\n```shell\nnpm install beeai-framework\n```\n\nFor more guidance and starter examples in your desired language, head to the docs pages for [Python](/python/README.md) and [TypeScript](/typescript/README.md).\n\n---\n\n## Quick example\n\nThis example demonstrates how to build a multi-agent workflow using BeeAI framework in Python.\n\n```py\nimport asyncio\nfrom beeai_framework.backend.chat import ChatModel\nfrom beeai_framework.tools.search.wikipedia import WikipediaTool\nfrom beeai_framework.tools.weather.openmeteo import OpenMeteoTool\nfrom beeai_framework.workflows.agent import AgentWorkflow, AgentWorkflowInput\n\nasync def main() -\u003e None:\n    llm = ChatModel.from_name(\"ollama:granite3.1-dense:8b\")\n    workflow = AgentWorkflow(name=\"Smart assistant\")\n\n    workflow.add_agent(\n        name=\"Researcher\",\n        role=\"A diligent researcher.\",\n        instructions=\"You look up and provide information about a specific topic.\",\n        tools=[WikipediaTool()],\n        llm=llm,\n    )\n\n    workflow.add_agent(\n        name=\"WeatherForecaster\",\n        role=\"A weather reporter.\",\n        instructions=\"You provide detailed weather reports.\",\n        tools=[OpenMeteoTool()],\n        llm=llm,\n    )\n\n    workflow.add_agent(\n        name=\"DataSynthesizer\",\n        role=\"A meticulous and creative data synthesizer\",\n        instructions=\"You can combine disparate information into a final coherent summary.\",\n        llm=llm,\n    )\n\n    location = \"Saint-Tropez\"\n\n    response = await workflow.run(\n        inputs=[\n            AgentWorkflowInput(\n                prompt=f\"Provide a short history of {location}.\",\n            ),\n            AgentWorkflowInput(\n                prompt=f\"Provide a comprehensive weather summary for {location} today.\",\n                expected_output=\"Essential weather details such as chance of rain, temperature and wind. Only report information that is available.\",\n            ),\n            AgentWorkflowInput(\n                prompt=f\"Summarize the historical and weather data for {location}.\",\n                expected_output=f\"A paragraph that describes the history of {location}, followed by the current weather conditions.\",\n            ),\n        ]\n    ).on(\n        \"success\",\n        lambda data, event: print(\n            f\"\\n-\u003e Step '{data.step}' has been completed with the following outcome.\\n\\n{data.state.final_answer}\"\n        ),\n    )\n\n    print(\"==== Final Answer ====\")\n    print(response.result.final_answer)\n\n\nif __name__ == \"__main__\":\n    asyncio.run(main())\n```\n\n_Source: [python/examples/workflows/multi_agents_simple.py](/python/examples/workflows/multi_agents.py)_\n\nTypeScript version of this example can be found [here](/typescript/examples/workflows/multiAgents.ts).\n\n### Running the example\n\n\u003e [!Note]\n\u003e\n\u003e To run this example, be sure that you have installed [ollama](https://ollama.com) with the [granite3.1-dense:8b](https://ollama.com/library/granite3.1-dense) model downloaded.\n\nTo run projects, use:\n\n```shell\npython [project_name].py\n```\n\nExplore more in our examples for [Python](/python/examples/README.md) and [TypeScript](/typescript/examples/README.md).\n\n---\n\n## Roadmap\n\n- Python parity with TypeScript\n- Standalone docs site\n- Integration with watsonx.ai for deployment\n- More multi-agent reference architecture implementations using workflows\n- More OTTB agent implementations\n- Native tool calling with supported LLM providers\n\nTo stay up-to-date on our [public roadmap](https://github.com/orgs/i-am-bee/projects/1/views/2).\n\n---\n\n## Contribution guidelines\n\nBeeAI framework is open-source and we ❤️ contributions.\u003cbr\u003e\n\nTo help build BeeAI, take a look at our:\n- [Python contribution guidelines](/python/CONTRIBUTING.md)\n- [TypeScript contribution guidelines](/typescript/CONTRIBUTING.md)\n\n## Bugs\n\nWe use GitHub Issues to manage bugs. Before filing a new issue, please check to make sure it hasn't already been logged. 🙏\n\n## Code of conduct\n\nThis project and everyone participating in it are governed by the [Code of Conduct](./CODE_OF_CONDUCT.md). By participating, you are expected to uphold this code. Please read the [full text](./CODE_OF_CONDUCT.md) so that you know which actions may or may not be tolerated.\n\n## Legal notice\n\nAll content in these repositories including code has been provided by IBM under the associated open source software license and IBM is under no obligation to provide enhancements, updates, or support. IBM developers produced this code as an open source project (not as an IBM product), and IBM makes no assertions as to the level of quality nor security, and will not be maintaining this code going forward.\n\n## Contributors\n\nSpecial thanks to our contributors for helping us improve BeeAI framework.\n\n\u003ca href=\"https://github.com/i-am-bee/beeai-framework/graphs/contributors\"\u003e\n  \u003cimg alt=\"Contributors list\" src=\"https://contrib.rocks/image?repo=i-am-bee/beeai-framework\" /\u003e\n\u003c/a\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/i-am-bee.github.io%2Fbeeai-framework%2F","html_url":"https://awesome.ecosyste.ms/projects/i-am-bee.github.io%2Fbeeai-framework%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/i-am-bee.github.io%2Fbeeai-framework%2F/lists"}