{"id":50852004,"url":"https://github.com/karem505/technical-support-agent","last_synced_at":"2026-06-14T14:04:30.056Z","repository":{"id":324109173,"uuid":"1095964673","full_name":"karem505/technical-support-agent","owner":"karem505","description":"this is a technical support agent that uses livekit and that will work on railway","archived":false,"fork":false,"pushed_at":"2025-12-31T15:19:52.000Z","size":176,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-14T14:04:28.714Z","etag":null,"topics":["ai","automation","fastapi","livekit","odoo","openai","python","voice-agent"],"latest_commit_sha":null,"homepage":null,"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/karem505.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-13T18:52:21.000Z","updated_at":"2025-12-31T15:19:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/karem505/technical-support-agent","commit_stats":null,"previous_names":["karem505/technical-support-agent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/karem505/technical-support-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/karem505%2Ftechnical-support-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/karem505%2Ftechnical-support-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/karem505%2Ftechnical-support-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/karem505%2Ftechnical-support-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/karem505","download_url":"https://codeload.github.com/karem505/technical-support-agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/karem505%2Ftechnical-support-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34324004,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-14T02:00:07.365Z","response_time":62,"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":["ai","automation","fastapi","livekit","odoo","openai","python","voice-agent"],"created_at":"2026-06-14T14:04:29.340Z","updated_at":"2026-06-14T14:04:30.045Z","avatar_url":"https://github.com/karem505.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Odoo Technical Support Agent\n\nAn AI-powered voice assistant for Odoo technical support with screen sharing capabilities and MCP (Model Context Protocol) integration.\n\n## Features\n\n- **Voice Interaction**: Natural voice conversations using LiveKit and OpenAI Realtime API\n- **Odoo Integration**: Direct access to Odoo instance via XML-RPC\n- **MCP Support**: Model Context Protocol for standardized AI tool interactions\n- **Screen Sharing**: Visual troubleshooting capabilities\n- **Railway Ready**: Optimized for easy deployment on Railway\n- **No Video Avatar**: Lightweight voice-only interface\n\n## Capabilities\n\nThe agent can help with:\n\n- Module installation, updates, and management\n- User account creation and password resets\n- Database queries and operations\n- Error diagnosis and log analysis\n- Configuration and troubleshooting\n- Best practices and guidance\n\n## Architecture\n\n```\ntechnical-support-agent/\n├── backend/\n│   ├── agent/          # LiveKit voice agent\n│   ├── api/            # FastAPI server\n│   └── mcp/            # MCP server for Odoo\n├── frontend/           # Next.js UI\n└── docs/              # Documentation\n```\n\n## Prerequisites\n\n- Python 3.11+\n- Node.js 20+\n- pnpm (recommended) or npm\n- LiveKit server (cloud or self-hosted)\n- OpenAI API key\n- Odoo instance (accessible via XML-RPC)\n\n## Quick Start\n\n### 1. Clone the repository\n\n```bash\ngit clone \u003cyour-repo-url\u003e\ncd technical-support-agent\n```\n\n### 2. Set up environment variables\n\n```bash\ncp .env.example .env\n```\n\nEdit `.env` with your credentials:\n\n```env\n# LiveKit Configuration\nLIVEKIT_URL=wss://your-livekit-server.livekit.cloud\nLIVEKIT_API_KEY=your-api-key\nLIVEKIT_API_SECRET=your-api-secret\n\n# OpenAI Configuration\nOPENAI_API_KEY=your-openai-api-key\n\n# Odoo Configuration\nODOO_HOST=your-odoo-instance.com\nODOO_PORT=8069\nODOO_DB=your-database-name\nODOO_USERNAME=admin\nODOO_PASSWORD=your-admin-password\n```\n\n### 3. Run with Docker Compose\n\n```bash\ndocker-compose up --build\n```\n\nThe services will be available at:\n- Frontend: http://localhost:3000\n- Backend API: http://localhost:8000\n\n### 4. Run locally (development)\n\n**Backend:**\n\n```bash\ncd backend\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\npip install -r requirements.txt\n\n# Start API server\npython -m uvicorn api.main:app --reload --port 8000\n\n# In another terminal, start the agent\npython -m agent.agent\n```\n\n**Frontend:**\n\n```bash\ncd frontend\npnpm install\npnpm dev\n```\n\n## Deploying to Railway\n\n### Option 1: Using Railway CLI\n\n1. Install Railway CLI:\n```bash\nnpm i -g @railway/cli\n```\n\n2. Login and initialize:\n```bash\nrailway login\nrailway init\n```\n\n3. Create two services (backend and frontend):\n\n**Backend:**\n```bash\nrailway up --service backend\n```\n\n**Frontend:**\n```bash\ncd frontend\nrailway up --service frontend\n```\n\n4. Set environment variables in Railway dashboard for each service\n\n### Option 2: Using Railway Dashboard\n\n1. Create a new project in Railway\n2. Add services:\n   - **Backend Service**:\n     - Root directory: `/backend`\n     - Build command: `pip install -r requirements.txt`\n     - Start command: `uvicorn api.main:app --host 0.0.0.0 --port $PORT`\n\n   - **Agent Service**:\n     - Root directory: `/backend`\n     - Build command: `pip install -r requirements.txt`\n     - Start command: `python -m agent.agent`\n\n   - **Frontend Service**:\n     - Root directory: `/frontend`\n     - Build command: `pnpm install \u0026\u0026 pnpm build`\n     - Start command: `pnpm start`\n\n3. Configure environment variables in each service\n4. Deploy!\n\n## MCP Server Usage\n\nThe MCP server provides standardized tools for Odoo operations:\n\n```bash\ncd backend\npython -m mcp.server\n```\n\nAvailable MCP tools:\n- `list_modules`: List all Odoo modules\n- `get_module_info`: Get module details\n- `list_users`: List all users\n- `get_user_details`: Get user information\n- `search_records`: Search any Odoo model\n- `get_database_info`: Get database info\n- `get_company_info`: Get company details\n- `check_module_dependencies`: Check module dependencies\n\n## Environment Variables\n\n### Backend\n\n| Variable | Description | Required |\n|----------|-------------|----------|\n| `LIVEKIT_URL` | LiveKit server WebSocket URL | Yes |\n| `LIVEKIT_API_KEY` | LiveKit API key | Yes |\n| `LIVEKIT_API_SECRET` | LiveKit API secret | Yes |\n| `OPENAI_API_KEY` | OpenAI API key | Yes |\n| `ODOO_HOST` | Odoo instance host | Yes |\n| `ODOO_PORT` | Odoo instance port | Yes |\n| `ODOO_DB` | Odoo database name | Yes |\n| `ODOO_USERNAME` | Odoo admin username | Yes |\n| `ODOO_PASSWORD` | Odoo admin password | Yes |\n| `ODOO_LOG_FILE` | Path to Odoo log file | No |\n| `PORT` | API server port | No (default: 8000) |\n\n### Frontend\n\n| Variable | Description | Required |\n|----------|-------------|----------|\n| `NEXT_PUBLIC_API_URL` | Backend API URL | Yes |\n| `NEXT_PUBLIC_LIVEKIT_URL` | LiveKit server URL | Yes |\n\n## Development\n\n### Adding New Odoo Tools\n\n1. Add the tool method in `backend/agent/tools.py`:\n\n```python\n@llm.ai_callable(description=\"Your tool description\")\nasync def your_tool(\n    self,\n    param: Annotated[str, llm.TypeInfo(description=\"Parameter description\")]\n) -\u003e str:\n    # Your implementation\n    pass\n```\n\n2. Register it in `backend/agent/agent.py`:\n\n```python\ntools=[\n    # ... existing tools\n    self.tools.your_tool,\n]\n```\n\n### Adding MCP Tools\n\n1. Implement the method in `backend/mcp/odoo_tools.py`\n2. Register it in `backend/mcp/server.py` in the `list_tools()` function\n3. Handle the call in `call_tool()` function\n\n## Troubleshooting\n\n### Connection Issues\n\n- Verify LiveKit credentials are correct\n- Check that Odoo instance is accessible\n- Ensure firewall allows WebSocket connections\n\n### Voice Not Working\n\n- Check browser microphone permissions\n- Verify OpenAI API key is valid\n- Check LiveKit server status\n\n### Odoo Connection Failed\n\n- Verify Odoo credentials\n- Check network connectivity to Odoo instance\n- Ensure Odoo XML-RPC is enabled\n\n## Security Considerations\n\n- Never commit `.env` file with credentials\n- Use Railway secrets for production credentials\n- Implement rate limiting for API endpoints\n- Use HTTPS/WSS in production\n- Restrict Odoo user permissions to minimum required\n\n## License\n\nMIT\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## Support\n\nFor issues and questions, please open an issue on GitHub.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkarem505%2Ftechnical-support-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkarem505%2Ftechnical-support-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkarem505%2Ftechnical-support-agent/lists"}