{"id":30656023,"url":"https://github.com/ryaneggz/langgraph-sandbox","last_synced_at":"2026-04-09T16:07:15.461Z","repository":{"id":311350823,"uuid":"1043025534","full_name":"ryaneggz/langgraph-sandbox","owner":"ryaneggz","description":"🦜🤖 LangGraph Sandbox for multi-agent AI workflows — with LinkedIn lead collector, Airtable sync, web search 🔍, VS Code ⚡, and Docker 🐳 support.","archived":false,"fork":false,"pushed_at":"2025-08-28T06:05:14.000Z","size":7494,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-28T12:49:12.178Z","etag":null,"topics":["agent-framework","ai-agents","automation","chatbot","deepagents","langchain","langgraph","llm","multi-agent","ollama","openai","python"],"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/ryaneggz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"security/auth.py","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-08-23T02:00:45.000Z","updated_at":"2025-08-28T06:05:17.000Z","dependencies_parsed_at":"2025-08-28T12:49:14.364Z","dependency_job_id":null,"html_url":"https://github.com/ryaneggz/langgraph-sandbox","commit_stats":null,"previous_names":["ryaneggz/langgraph-starter","ryaneggz/langgraph-sandbox"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/ryaneggz/langgraph-sandbox","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryaneggz%2Flanggraph-sandbox","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryaneggz%2Flanggraph-sandbox/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryaneggz%2Flanggraph-sandbox/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryaneggz%2Flanggraph-sandbox/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ryaneggz","download_url":"https://codeload.github.com/ryaneggz/langgraph-sandbox/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryaneggz%2Flanggraph-sandbox/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272965497,"owners_count":25023071,"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","status":"online","status_checked_at":"2025-08-31T02:00:09.071Z","response_time":79,"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":["agent-framework","ai-agents","automation","chatbot","deepagents","langchain","langgraph","llm","multi-agent","ollama","openai","python"],"created_at":"2025-08-31T10:03:35.101Z","updated_at":"2026-04-09T16:07:15.426Z","avatar_url":"https://github.com/ryaneggz.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LangGraph Starter\n\nA LangGraph-based starter template for building **collections of AI agents**. This template provides a foundation for creating multi-agent systems with capabilities like LinkedIn lead collection, web search, and Airtable data integration.\n\n---\n\n## ✨ Features\n\n- Collection of configurable AI agents using **DeepAgents** and **LangGraph**\n- Agent entrypoints defined in `langgraph.json` for easy management\n- Example: **LinkedIn Lead Collector** agent\n- **Airtable** integration for structured data storage\n- Built-in **web search** tools\n- **VS Code** debugging configuration included\n- **Docker**-ready for containerized development \u0026 deployment\n\n---\n\n## 🚀 Quick Start\n\n### Prerequisites\n- **Python 3.11+**\n- **Docker** (optional, for containerized deployment)\n\n### Installation\n\n1. **Clone the repository**\n   ```bash\n   git clone \u003cYOUR_REPO_URL\u003e langgraph-starter\n   cd langgraph-starter\n   ```\n\n2. **Install dependencies with uv (recommended)**\n\n   ```bash\n   uv venv\n   source .venv/bin/activate\n   uv sync\n   ```\n\n3. **Set up environment variables**\n\n   ```bash\n   cp .env.example .env\n   # Edit .env with your API keys and configuration\n   ```\n\n4. **Start the development server**\n\n   ```bash\n   make dev\n   ```\n\n### MCP Server\n\nThis project includes an **MCP (Model Context Protocol) server** for enhanced AI integrations.\n\n**Start the MCP server:**\n\n```bash\npython mcp\n```\n   \n---\n\n## 🖥️ Recommended LangGraph UIs\n\n* **[LangGraph Studio](https://smith.langchain.com/studio)** — Official Studio for visual graph editing \u0026 monitoring\n* **[Agent Chat UI](https://agentchat.vercel.app)** — Clean chat interface for testing your agents\n\n---\n\n## 🛠️ Development \u0026 Debugging\n\n* **`.vscode/launch.json`** is pre-configured for:\n\n  * **Attach to LangGraph** — Debug a running server on port `5678`\n  * **Debug Script** — Run and debug individual scripts\n\n**Steps:**\n\n1. Run:\n\n   ```bash\n   make debug\n   ```\n2. In VS Code, press **F5** and select **Attach to LangGraph**.\n\n---\n\n## 🗂️ Project Structure\n\n```text\nlanggraph-starter/\n├─ agents/\n│  └─ linkedin_leads.py          # LinkedIn lead collection agent (example)\n├─ tools/\n│  ├─ __init__.py\n│  ├─ airtable.py                # Airtable integration tools\n│  └─ search.py                  # Web search tools\n├─ .vscode/\n│  └─ launch.json                # VS Code debug config\n├─ docker-compose.yml            # Docker services\n├─ langgraph.json                # LangGraph configuration\n├─ Makefile                      # Dev commands\n├─ pyproject.toml                # Python project configuration\n└─ .env.example                  # Example environment variables\n```\n\n---\n\n## 🧰 Commands\n\n### Make targets\n\n```bash\nmake dev      # Start development server\nmake debug    # Start with debugging enabled (port 5678)\nmake build    # Build and push Docker image\n```\n\n### Using the LangGraph CLI directly\n\n```bash\nlanggraph dev                       # Start dev server\nlanggraph dev --debug-port 5678     # Start with debugging\nlanggraph build                     # Build the application\n```\n\n---\n\n## 🧠 How It Works\n\n### Agent Architecture\n\n* **Modular Design** — Each agent is a separate module under `agents/`\n* **LangGraph Integration** — Agents and entrypoints are declared in `langgraph.json`\n* **Tooling** — Shared tools under `tools/` (e.g., Airtable, search) can be reused\n* **State \u0026 Orchestration** — LangGraph coordinates agent state and message flow\n\n### Included Example Agents\n\n1. **LinkedIn Lead Collector** — Searches LinkedIn for potential leads (example logic)\n2. **Note Taker** — Normalizes and organizes collected data\n3. **Airtable Integration** — Persists structured results to Airtable\n\n### Adding a New Agent\n\n1. Create a new file under `agents/` (e.g., `my_agent.py`)\n2. Register it in `langgraph.json` (entrypoints, graph configuration)\n3. Wire up any shared tools you need from `tools/`\n\n---\n\n## ⚙️ Configuration\n\nKey files:\n\n* `langgraph.json` — Graphs and entrypoints\n* `.env` — Environment variables and API keys\n* `pyproject.toml` — Python dependencies and project metadata\n* `.vscode/launch.json` — VS Code debugging configuration\n\n\u003e Tip: Ensure any secrets (API keys, tokens) are only in `.env` and **excluded** from version control.\n\n---\n\n## 🐳 Docker (optional)\n\nBuild and run with Docker:\n\n```bash\ndocker compose up --build\n```\n\nMount local files (e.g., `/files`) via `docker-compose.yml` volumes for read/write access.\n\n---\n\n## 🤝 Contributing\n\n1. Fork the repo\n2. Create a feature branch:\n\n   ```bash\n   git checkout -b feature/amazing-feature\n   ```\n3. Commit:\n\n   ```bash\n   git commit -m \"Add amazing feature\"\n   ```\n4. Push:\n\n   ```bash\n   git push origin feature/amazing-feature\n   ```\n5. Open a Pull Request\n\n---\n\n## 📄 License\n\nThis project is licensed under the terms specified in the **LICENSE** file.\n\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryaneggz%2Flanggraph-sandbox","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fryaneggz%2Flanggraph-sandbox","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryaneggz%2Flanggraph-sandbox/lists"}