{"id":26436273,"url":"https://github.com/chenxingqiang/agent-flow-project","last_synced_at":"2025-03-18T08:16:05.366Z","repository":{"id":269377196,"uuid":"898275257","full_name":"chenxingqiang/agent-flow-project","owner":"chenxingqiang","description":"A Python, JavaScript, CSS project focusing on Project Structure, Create and initialize agent, Workflow execution, Configuration, Core component tests.","archived":false,"fork":false,"pushed_at":"2025-02-17T02:27:08.000Z","size":2138,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-15T18:53:25.844Z","etag":null,"topics":["agent","agentflow","css","flow","html","javascript","jinja","project","python","shell","tex"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chenxingqiang.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":"2024-12-04T05:24:53.000Z","updated_at":"2025-02-26T04:09:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"50bc840b-c6ad-41a9-a8f2-366b2949ce16","html_url":"https://github.com/chenxingqiang/agent-flow-project","commit_stats":null,"previous_names":["chenxingqiang/agentflow","chenxingqiang/agent-flow-project"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chenxingqiang%2Fagent-flow-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chenxingqiang%2Fagent-flow-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chenxingqiang%2Fagent-flow-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chenxingqiang%2Fagent-flow-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chenxingqiang","download_url":"https://codeload.github.com/chenxingqiang/agent-flow-project/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244181387,"owners_count":20411605,"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":["agent","agentflow","css","flow","html","javascript","jinja","project","python","shell","tex"],"created_at":"2025-03-18T08:16:04.187Z","updated_at":"2025-03-18T08:16:05.361Z","avatar_url":"https://github.com/chenxingqiang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AgentFlow\n\nAgentFlow is a flexible and extensible framework for building and managing AI agents and workflows. It provides a modular architecture for creating, configuring, and orchestrating AI agents with advanced features for workflow management and testing.\n\n## Latest Version\n\nCurrent version: v0.1.1\n- Fixed workflow transform functions to handle step and context parameters\n- Added feature engineering and outlier removal transforms\n- Improved test suite and type hints\n- Enhanced error handling and validation\n\n## Project Structure\n\n```\nagentflow/\n├── agents/             # Agent implementations\n│   ├── agent.py       # Base agent implementation\n│   └── agent_types.py # Agent type definitions\n├── core/              # Core framework components\n│   ├── base_types.py  # Base type definitions\n│   ├── config.py      # Configuration management\n│   ├── workflow.py    # Workflow engine\n│   └── workflow_executor.py # Workflow execution\n├── ell2a/             # ELL2A integration\n│   └── types/         # Message and content types\n├── transformations/   # Data transformation tools\n│   └── text.py       # Text processing utilities\n└── tests/            # Comprehensive test suite\n    ├── unit/         # Unit tests\n    ├── core/         # Core component tests\n    └── performance/  # Performance tests\n```\n\n## Features\n\n- **Flexible Agent Architecture**\n  - Configurable agent types and behaviors\n  - Support for research and data science agents\n  - Extensible agent factory system\n\n- **Advanced Workflow Management**\n  - Step-based workflow execution\n  - Dependency management\n  - Error handling and retry policies\n  - Performance monitoring\n\n- **Robust Testing Framework**\n  - Unit and integration tests\n  - Performance testing\n  - Test-driven development support\n\n- **Data Transformation Tools**\n  - Feature engineering\n  - Outlier removal\n  - Text processing utilities\n\n- **Type Safety**\n  - Comprehensive type hints\n  - Pydantic model validation\n  - Runtime type checking\n\n## Installation\n\n```bash\npip install agentflow\n```\n\n## Quick Start\n\n```python\nfrom agentflow import Agent, AgentConfig, WorkflowConfig, WorkflowStep, WorkflowStepType\n\n# Create workflow configuration\nworkflow_config = WorkflowConfig(\n    id=\"test-workflow\",\n    name=\"test_workflow\",\n    steps=[\n        WorkflowStep(\n            id=\"step-1\",\n            name=\"transform_step\",\n            type=WorkflowStepType.TRANSFORM,\n            description=\"Data transformation step\",\n            config={\n                \"strategy\": \"standard\",\n                \"params\": {\n                    \"method\": \"standard\",\n                    \"with_mean\": True,\n                    \"with_std\": True\n                }\n            }\n        )\n    ]\n)\n\n# Create agent configuration\nagent_config = AgentConfig(\n    name=\"test_agent\",\n    type=\"data_science\",\n    workflow=workflow_config\n)\n\n# Create and initialize agent\nagent = Agent(config=agent_config)\nawait agent.initialize()\n\n# Process data\nresult = await agent.execute({\"data\": your_data})\n```\n\n## Configuration\n\nAgents and workflows can be configured using Python dictionaries or YAML files:\n\n```yaml\nAGENT:\n  name: data_science_agent\n  type: data_science\n  version: 1.0.0\n  mode: sequential\n\nMODEL:\n  provider: openai\n  name: gpt-4\n  temperature: 0.7\n  max_tokens: 4096\n\nWORKFLOW:\n  id: transform-workflow\n  name: Data Transformation Workflow\n  max_iterations: 5\n  timeout: 30\n  steps:\n    - id: step-1\n      name: feature_engineering\n      type: transform\n      description: Feature engineering step\n      config:\n        strategy: standard\n        params:\n          method: standard\n          with_mean: true\n          with_std: true\n```\n\n## Testing\n\nRun the test suite:\n\n```bash\n# Run all tests\npytest\n\n# Run specific test categories\npytest tests/unit/\npytest tests/core/\npytest tests/performance/\n```\n\n## Contributing\n\n1. Fork the repository\n2. Create a feature branch\n3. Write tests for your changes\n4. Implement your changes\n5. Run the test suite\n6. Create a Pull Request\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchenxingqiang%2Fagent-flow-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchenxingqiang%2Fagent-flow-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchenxingqiang%2Fagent-flow-project/lists"}