{"id":28416082,"url":"https://github.com/micpec/agentgenius","last_synced_at":"2025-06-26T14:31:36.363Z","repository":{"id":274340800,"uuid":"917337874","full_name":"MicPec/AgentGENius","owner":"MicPec","description":"AgentGENius is an  AI agent framework, built on top of Pydantic AI, that enables intelligent task execution and automation through a combination of natural language processing and modular tool integration (also auto-generated).","archived":false,"fork":false,"pushed_at":"2025-02-04T20:45:18.000Z","size":922,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-04T03:57:52.262Z","etag":null,"topics":["agents","autogenerated","framework","pydantic-ai"],"latest_commit_sha":null,"homepage":"","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/MicPec.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-01-15T19:47:14.000Z","updated_at":"2025-02-04T20:45:21.000Z","dependencies_parsed_at":"2025-01-26T18:27:12.090Z","dependency_job_id":"c81ad53f-832e-4bba-bb7d-79f0f9bfe3f5","html_url":"https://github.com/MicPec/AgentGENius","commit_stats":null,"previous_names":["micpec/agentgenius"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/MicPec/AgentGENius","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MicPec%2FAgentGENius","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MicPec%2FAgentGENius/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MicPec%2FAgentGENius/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MicPec%2FAgentGENius/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MicPec","download_url":"https://codeload.github.com/MicPec/AgentGENius/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MicPec%2FAgentGENius/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262084740,"owners_count":23256292,"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","autogenerated","framework","pydantic-ai"],"created_at":"2025-06-03T20:07:35.392Z","updated_at":"2025-06-26T14:31:36.354Z","avatar_url":"https://github.com/MicPec.png","language":"Python","readme":"```\n                          _    _____ ______ _   _ _           \n    /\\                   | |  / ____|  ____| \\ | (_)          \n   /  \\   __ _  ___ _ __ | |_| |  __| |__  |  \\| |_ _   _ ___ \n  / /\\ \\ / _` |/ _ \\ '_ \\| __| | |_ |  __| | . ` | | | | / __|\n / ____ \\ (_| |  __/ | | | |_| |__| | |____| |\\  | | |_| \\__ \\\n/_/    \\_\\__, |\\___|_| |_|\\__|\\_____|______|_| \\_|_|\\__,_|___/\n          __/ |                                               \n         |___/                                                \n```\n\n\n# AgentGENius\n\nAgentGENius is a powerful AI agent framework, built on top of Pydantic AI, that enables intelligent task execution and automation through a combination of natural language processing and modular tool integration (also auto-generated).\n\n## Features\n\n- **Intelligent Task Management**: Breaks down complex tasks into manageable subtasks\n- **Built-in Tools**: Comprehensive set of built-in tools for file operations, web searches, and system interactions\n- **Task History**: Maintains a history of executed tasks and their results\n- **Extensible Architecture**: Easy integration of new tools and capabilities\n- **Streamlit Interface**: Example web interface for interacting with the agent\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/MicPec/AgentGENius.git\ncd AgentGENius\n```\n\n2. Create and activate a virtual environment:\n```bash\nuv sync\n```\n\n3. Add API keys to the `.env` file:\n```code\nOPENAI_API_KEY=\"sk-proj-****\"\nTAVILY_API_KEY=\"tvly-****\"\n```\nThose two keys can be obtained from the [OpenAI API](https://platform.openai.com) and [Tavily API](https://app.tavily.com/) websites.\n## Usage\n\n### CLI Chat Application\n\n1. Start the CLI chat application:\n```bash\nuv run example.py\n```\n\n### Streamlit Interface\n\n1. Start the Streamlit interface:\n```bash\nuv run streamlit run streamlit_app.py --server.headless=true\n```\n\n2. Open your browser and navigate to the displayed URL (typically http://localhost:8501)\n\n3. Enter your queries in natural language and let AgentGENius handle the rest!\n\n## Flow\n\nThe following diagram shows the high-level architecture and flow of AgentGENius:\n\n```mermaid\ngraph TB\n    User((User)) --\u003e |Query| AG[AgentGENius]\n    AG --\u003e QA[Question Analyzer]\n\n    subgraph Processing [Task Processing]\n        QA --\u003e Tasks[Subtasks]\n        Tasks --\u003e TM[Tool Manager]\n        TM --\u003e |Existing Tools| TR[Task Runner]\n        TM --\u003e |New Tool Needed| TC[Tool Coder]\n        TC --\u003e |Generated Tool| TR\n        TR --\u003e |Task Results| AGG[Aggregator]\n    end\n    \n    AGG --\u003e Response[Response]\n    Response --\u003e User\n    Response -.-\u003e History\n    \n    subgraph Support [Supporting Systems]\n        Tools[Tool Registry]\n        History[Task History]\n    end\n    \n    TC --\u003e Tools\n    Tools -.-\u003e TM \u0026 TR\n    History -.-\u003e AGG \u0026 QA\n\n\n    style User fill:#373,color:#fff\n    style AG fill:#22e,color:#fff\n    style Response fill:#b33,color:#fff\n\n```\n\nThe flow consists of several key components:\n\n1. **Question Analyzer**: Breaks down user queries into manageable subtasks\n2. **Tool Manager**: Identifies and manages tools needed for each task\n3. **Tool Coder**: Generates new tools when required\n4. **Task Runner**: Executes tasks using available tools\n5. **Aggregator**: Combines task results into coherent responses\n\nSupporting components include:\n- **Task History**: Maintains conversation context\n- **Tool Registry**: Manages available tools and their definitions\n- **Callback System**: Provides real-time status updates (not on the diagram for readability) \n\n## Project Structure\n\n```\nAgentGENius/\n├── agentgenius/          # Core package\n│   ├── main.py           # Main agent implementation\n│   ├── builtin_tools.py  # Built-in tool definitions\n│   ├── config.py         # Configuration settings\n│   └── ...\n├── history/              # Task history storage\n├── streamlit_app.py      # Example Streamlit web interface\n├── example.py            # Example CLI chat application\n└── pyproject.toml        # Project dependencies\n```\nTools generated by AgentGENius are stored in the `{TEMP}/agentgenius/tools` directory.\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmicpec%2Fagentgenius","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmicpec%2Fagentgenius","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmicpec%2Fagentgenius/lists"}