{"id":28160135,"url":"https://github.com/daymade/agenty","last_synced_at":"2025-10-23T20:39:31.585Z","repository":{"id":287936195,"uuid":"966292062","full_name":"daymade/agenty","owner":"daymade","description":null,"archived":false,"fork":false,"pushed_at":"2025-04-22T09:35:53.000Z","size":1240,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-22T09:46:02.792Z","etag":null,"topics":[],"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/daymade.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,"zenodo":null}},"created_at":"2025-04-14T17:42:19.000Z","updated_at":"2025-04-17T10:26:40.000Z","dependencies_parsed_at":"2025-04-22T09:33:39.004Z","dependency_job_id":null,"html_url":"https://github.com/daymade/agenty","commit_stats":null,"previous_names":["daymade/agenty"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daymade%2Fagenty","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daymade%2Fagenty/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daymade%2Fagenty/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daymade%2Fagenty/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/daymade","download_url":"https://codeload.github.com/daymade/agenty/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254319660,"owners_count":22051076,"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":[],"created_at":"2025-05-15T10:12:53.554Z","updated_at":"2025-10-23T20:39:31.526Z","avatar_url":"https://github.com/daymade.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PPA New Business AI Agent\n\nAn AI Agent using LangGraph to automate the initial stages of Personal Private Auto (PPA) insurance new business quoting process within an insurance company.\n\n## Overview\n\nThis project implements a Proof of Concept (PoC) AI Agent that:\n- Processes customer email inquiries for new PPA insurance quotes\n- Extracts relevant information\n- Manages the quote request workflow\n- Integrates with human agents for review and approval\n\nFor detailed system design, see [System Design Document](docs/system_design.md).\n\n## Setup\n\n### Prerequisites\n\n- [Conda](https://docs.conda.io/en/latest/) for environment management\n- Python 3.11+\n- Google Gemini API key or OpenAI API key\n\n### Environment Setup\n\n1. Clone the repository:\n```bash\ngit clone \u003crepository-url\u003e\ncd ppa-agent\n```\n\n2. Create and activate the Conda environment:\n```bash\nconda env create -f environment.yml\nconda activate ppa-agent\n```\n\n3. Create a `.env` file in the project root:\n```bash\n# For Gemini API (recommended)\nGEMINI_API_KEY=your_gemini_api_key_here\n\n# Or for OpenAI (alternative)\nOPENAI_API_KEY=your_openai_api_key_here\n```\n\n## Project Structure\n\n```\n.\n├── docs/\n│   ├── system_design.md          # Detailed system design documentation\n│   ├── google_genai_migration.md # Migration guide for google-genai SDK\n│   ├── dev_logs.md               # Chronological development logs\n│   └── todo.md                   # Implementation plan\n├── src/\n│   ├── __init__.py\n│   ├── ppa_agent.py              # Main agent implementation\n│   └── visualize_agent.py        # LangGraph UI visualization script\n├── tests/\n│   └── __init__.py\n├── .env                          # Environment variables (not in git)\n├── .gitignore\n├── environment.yml               # Conda environment specification\n└── README.md\n```\n\n## Model Support\n\nThis project supports multiple LLM providers:\n\n- **Gemini** (Primary): Using Google's `google-genai` SDK with Gemini 2.5 Pro models\n- **OpenAI** (Alternative): Using GPT models via the OpenAI API\n\n\u003e **Note**: The project has migrated from `google-generativeai` to the newer `google-genai` SDK.\n\u003e For details on this migration, see the [Google Genai Migration Guide](docs/google_genai_migration.md).\n\n## Workflow Visualization\n\nThis project includes LangGraph UI visualization to help understand and debug the agent workflow:\n\n1. Run the visualization script:\n```bash\npython -m src.visualize_agent\n```\n\n2. This will generate two HTML files in the `visualizations` directory:\n   - `agent_workflow.html`: Shows the agent's workflow graph with nodes and transitions\n   - `agent_trace.html`: Demonstrates a trace of a sample execution\n\n3. Open these HTML files in your browser to interact with the visualizations.\n\nThe workflow visualization provides:\n- Visual representation of the agent's state machine\n- Step-by-step execution tracing\n- Node and edge details\n- Visibility into LLM calls and state transitions\n\n## Development\n\nFollow the implementation plan in `docs/todo.md` for step-by-step development guidance.\n\n## Testing\n\nRun the test suite using pytest:\n\n```bash\npoetry run pytest\n```\n\n## Contributing\n\n1. Create a feature branch\n2. Make your changes\n3. Submit a pull request\n\n## License\n\n(To be determined)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaymade%2Fagenty","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdaymade%2Fagenty","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaymade%2Fagenty/lists"}