{"id":48867244,"url":"https://github.com/kryvokhyzha/langgraph-agent-toolkit","last_synced_at":"2026-04-15T19:40:09.924Z","repository":{"id":288910368,"uuid":"962052929","full_name":"kryvokhyzha/langgraph-agent-toolkit","owner":"kryvokhyzha","description":"A comprehensive toolkit for building, deploying, and managing AI agents using LangGraph, FastAPI, and Streamlit. It provides a production-ready framework for creating conversational AI agents with features like multi-provider LLM support, streaming responses, observability, memory and prompt management.","archived":false,"fork":false,"pushed_at":"2026-01-30T19:59:45.000Z","size":12440,"stargazers_count":9,"open_issues_count":2,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-31T12:06:09.648Z","etag":null,"topics":["fastapi","langchain","langgraph","streamlit"],"latest_commit_sha":null,"homepage":"https://kryvokhyzha.github.io/langgraph-agent-toolkit","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/kryvokhyzha.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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":"2025-04-07T15:18:14.000Z","updated_at":"2026-01-30T19:55:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"bbc54ee8-d00f-4875-9dd1-4bc22ae1dad3","html_url":"https://github.com/kryvokhyzha/langgraph-agent-toolkit","commit_stats":null,"previous_names":["kryvokhyzha/langgraph-agent-toolkit"],"tags_count":50,"template":true,"template_full_name":"JoshuaC215/agent-service-toolkit","purl":"pkg:github/kryvokhyzha/langgraph-agent-toolkit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kryvokhyzha%2Flanggraph-agent-toolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kryvokhyzha%2Flanggraph-agent-toolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kryvokhyzha%2Flanggraph-agent-toolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kryvokhyzha%2Flanggraph-agent-toolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kryvokhyzha","download_url":"https://codeload.github.com/kryvokhyzha/langgraph-agent-toolkit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kryvokhyzha%2Flanggraph-agent-toolkit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31857616,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-15T15:24:51.572Z","status":"ssl_error","status_checked_at":"2026-04-15T15:24:39.138Z","response_time":63,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["fastapi","langchain","langgraph","streamlit"],"created_at":"2026-04-15T19:40:09.039Z","updated_at":"2026-04-15T19:40:09.909Z","avatar_url":"https://github.com/kryvokhyzha.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n   \u003cimg alt=\"LangGraph Agent Toolkit Logo\" src=\"https://raw.githubusercontent.com/kryvokhyzha/langgraph-agent-toolkit/main/docs/media/logo.svg\" width=\"300\"\u003e\n\u003c/div\u003e\n\n---\n\n# 🧰 LangGraph Agent Toolkit\n\n|            |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |\n| ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| CI/Testing | [![build status](https://github.com/kryvokhyzha/langgraph-agent-toolkit/actions/workflows/test.yml/badge.svg)](https://github.com/kryvokhyzha/langgraph-agent-toolkit/actions/workflows/test.yml) [![docs status](https://github.com/kryvokhyzha/langgraph-agent-toolkit/actions/workflows/sphinx.yml/badge.svg)](https://github.com/kryvokhyzha/langgraph-agent-toolkit/actions/workflows/sphinx.yml) [![codecov](https://codecov.io/gh/kryvokhyzha/langgraph-agent-toolkit/graph/badge.svg?token=OHSACTNSWZ)](https://codecov.io/gh/kryvokhyzha/langgraph-agent-toolkit) |\n| Package    | [![PyPI version](https://img.shields.io/pypi/v/langgraph-agent-toolkit.svg)](https://pypi.org/project/langgraph-agent-toolkit/) [![PyPI Downloads](https://img.shields.io/pypi/dm/langgraph-agent-toolkit.svg)](https://pypi.org/project/langgraph-agent-toolkit/) [![Python Version](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Fkryvokhyzha%2Flanggraph-agent-toolkit%2Fmain%2Fpyproject.toml)](https://github.com/kryvokhyzha/langgraph-agent-toolkit/blob/main/pyproject.toml)                          |\n| Meta       | [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff) [![GitHub License](https://img.shields.io/github/license/kryvokhyzha/langgraph-agent-toolkit)](https://github.com/kryvokhyzha/langgraph-agent-toolkit/blob/main/LICENSE)                                                                                                                                                                                                                                      |\n\n\u003c!-- [![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_red.svg)](https://langgraph-agent-toolkit.streamlit.app/) --\u003e\n\n## 📋 Introduction\n\nA comprehensive toolkit for building, deploying, and managing AI agents using\nLangGraph, FastAPI, and Streamlit. It provides a production-ready framework for\ncreating conversational AI agents with features like multi-provider LLM support,\nstreaming responses, observability, memory and prompt management.\n\n### What is langGraph-agent-toolkit?\n\nThe langgraph-agent-toolkit is a full-featured framework for developing and\ndeploying AI agent services. Built on the foundation of:\n\n- **[LangGraph](https://langchain-ai.github.io/langgraph/)** for agent creation\n  with advanced flows and human-in-the-loop capabilities\n- **[FastAPI](https://fastapi.tiangolo.com/)** for robust, high-performance API\n  services with streaming support\n- **[Streamlit](https://streamlit.io/)** for intuitive user interfaces\n\nKey components include:\n\n- Data structures and settings built with\n  **[Pydantic](https://github.com/pydantic/pydantic)**\n- **[LiteLLM](https://github.com/BerriAI/litellm)** proxy for universal\n  multi-provider LLM support\n- Comprehensive memory management and persistence using PostgreSQL/SQLite\n- Advanced observability tooling via Langfuse and Langsmith\n- Modular architecture allowing customization while maintaining a consistent\n  application structure\n\nWhether you're building a simple chatbot or complex multi-agent system, this\ntoolkit provides the infrastructure to develop, test, and deploy your\nLangGraph-based agents with confidence.\n\nYou can use [DeepWiki](https://deepwiki.com/kryvokhyzha/langgraph-agent-toolkit)\nto learn more about this repository.\n\n## 📑 Contents\n\n- [Introduction](#-introduction)\n- [Quickstart](#-quickstart)\n- [Installation Options](#-installation-options)\n- [Architecture](#architecture)\n- [Key Features](#-key-features)\n- [Environment Setup](#environment-setup)\n- [Project Structure](#-project-structure)\n- [Setup and Usage](#setup-and-usage)\n- [Documentation](#-documentation)\n- [Useful Resources](#-useful-resources)\n- [Development and Contributing](#-development-and-contributing)\n- [License](#-license)\n\n## 🚀 Quickstart\n\n1. Create a `.env` file based on [`.env.example`](./.env.example)\n\n2. **Option 1: Run with Python from source**\n\n   ```sh\n   # Install dependencies\n   pip install uv\n   uv sync --frozen\n   source .venv/bin/activate\n\n   # Start the service\n   python langgraph_agent_toolkit/run_api.py\n\n   # In another terminal\n   source .venv/bin/activate\n   streamlit run langgraph_agent_toolkit/run_app.py\n   ```\n\n3. **Option 2: Run with Python from PyPi repository**\n\n   ```sh\n   pip install langgraph-agent-toolkit\n   ```\n\n   ℹ️ For more details on installation options, see the\n   [Installation Documentation](docs/installation.rst).\n\n4. **Option 3: Run with Docker**\n\n   ```sh\n   docker compose watch\n   ```\n\n\u003ca name=\"installation-options\"\u003e\u003c/a\u003e\n\n## 📦 Installation Options\n\nThe toolkit supports multiple installation options using \"extras\" to include\njust the dependencies you need.\n\nFor detailed installation instructions and available extras, see the\n[Installation Documentation](docs/installation.rst).\n\n\u003ca name=\"architecture\"\u003e\u003c/a\u003e\n\n## 🏗️ Architecture\n\n\u003cimg src=\"https://raw.githubusercontent.com/kryvokhyzha/langgraph-agent-toolkit/main/docs/media/agent_architecture.png\" width=\"800\"\u003e\n\n\u003ca name=\"key-features\"\u003e\u003c/a\u003e\n\n## ✨ Key Features\n\n1. **LangGraph Integration**\n\n   - Latest LangGraph v0.3 features\n   - Human-in-the-loop with `interrupt()`\n   - Flow control with `Command` and `langgraph-supervisor`\n\n2. **API Service**\n\n   - FastAPI with streaming and non-streaming endpoints\n   - Support for both token-based and message-based streaming\n   - Multiple agent support with URL path routing\n   - Available agents and models listed at `/info` endpoint\n   - Supports different runners (unicorn, gunicorn, mangum, azure functions)\n\n3. **Developer Experience**\n\n   - Asynchronous design with async/await\n   - Docker configuration with live reloading\n   - Comprehensive testing suite\n\n4. **Enterprise Components**\n   - Configurable PostgreSQL/SQLite connection pools\n   - Observability via Langfuse and Langsmith\n   - User feedback system\n   - Prompt management system\n   - LiteLLM proxy integration\n\nFor more details on features, see the [Usage Documentation](docs/usage.rst).\n\n\u003ca name=\"environment-setup\"\u003e\u003c/a\u003e\n\n## ⚙️ Environment Setup\n\nFor detailed environment setup instructions, including creating your `.env` file\nand configuring LiteLLM, see the\n[Environment Setup Documentation](docs/environment_setup.rst).\n\n\u003ca name=\"project-structure\"\u003e\u003c/a\u003e\n\n## 📂 Project Structure\n\nThe repository contains:\n\n- `langgraph_agent_toolkit/agents/blueprints/`: Agent definitions\n- `langgraph_agent_toolkit/agents/agent_executor.py`: Agent execution control\n- `langgraph_agent_toolkit/schema/`: Protocol schema definitions\n- `langgraph_agent_toolkit/core/`: Core modules (LLM, memory, settings)\n- `langgraph_agent_toolkit/service/service.py`: FastAPI service\n- `langgraph_agent_toolkit/client/client.py`: Service client\n- `langgraph_agent_toolkit/run_app.py`: Chat interface\n- `docker/`: Docker configurations\n- `tests/`: Test suite\n\n\u003ca name=\"setup-and-usage\"\u003e\u003c/a\u003e\n\n## 🛠️ Setup and Usage\n\nFor detailed setup and usage instructions, including building your own agent,\nDocker setup, using the AgentClient, and local development, see the\n[Usage Documentation](docs/usage.rst).\n\n\u003ca name=\"documentation\"\u003e\u003c/a\u003e\n\n## 📚 Documentation\n\nFull documentation is available at\n[GitHub repository](https://github.com/kryvokhyzha/langgraph-agent-toolkit/tree/main/docs/)\nand includes:\n\n- [Installation Guide](https://github.com/kryvokhyzha/langgraph-agent-toolkit/blob/main/docs/installation.rst)\n- [Environment Setup](https://github.com/kryvokhyzha/langgraph-agent-toolkit/blob/main/docs/environment_setup.rst)\n- [Usage Guide](https://github.com/kryvokhyzha/langgraph-agent-toolkit/blob/main/docs/usage.rst)\n\n\u003ca name=\"useful-resources\"\u003e\u003c/a\u003e\n\n## 📚 Useful Resources\n\n- [LangGraph documentation](https://langchain-ai.github.io/langgraph/concepts/low_level/#multiple-schemas)\n- [LangGraph Memory Concept](https://langchain-ai.github.io/langgraph/concepts/memory/)\n- [LangGraph Memory Persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/#memory)\n- [LangGraph Memory Template](https://github.com/langchain-ai/memory-template)\n- [LangGraph Human in the Loop](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/wait-user-input/)\n- [LangGraph 101 - blueprints](https://github.com/langchain-ai/langgraph-101)\n- [LangGraph - Examples](https://github.com/langchain-ai/langgraph/tree/main/examples)\n- [Complex data extraction with function calling](https://langchain-ai.github.io/langgraph/tutorials/extraction/retries/)\n- [How to edit graph state](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/edit-graph-state/)\n- [Memory in the background](https://www.youtube.com/watch?v=R1jKQ1Jn5T4\u0026ab_channel=LangChain)\n- [Building an agent with LangGraph](https://www.kaggle.com/code/markishere/day-3-building-an-agent-with-langgraph/)\n- [How to create tools in Langchain](https://python.langchain.com/docs/how_to/custom_tools/)\n- [Simple Serverless FastAPI with AWS Lambda](https://www.deadbear.io/simple-serverless-fastapi-with-aws-lambda/)\n- [LangGraph Middleware](https://docs.langchain.com/oss/python/langchain/middleware)\n\n\u003ca name=\"development-and-contributing\"\u003e\u003c/a\u003e\n\n## 👥 Development and Contributing\n\nThank you for considering contributing to `Langgraph Agent Toolkit`! We\nencourage the community to post Issues and Pull Requests.\n\nBefore you get started, please see our [Contribution Guide](CONTRIBUTING.md).\n\n\u003ca name=\"license\"\u003e\u003c/a\u003e\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the LICENSE file for\ndetails.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkryvokhyzha%2Flanggraph-agent-toolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkryvokhyzha%2Flanggraph-agent-toolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkryvokhyzha%2Flanggraph-agent-toolkit/lists"}