Welcome to Awesome LangGraph Agents - a comprehensive collection of sophisticated AI agents built using the latest LangGraph framework. Each agent demonstrates best practices in agentic AI development, featuring multi-step reasoning, tool orchestration, and production-ready architectures.

• 🔄 Stateful Workflows: Build complex, multi-step agent workflows with persistent state
• 🛠️ Tool Integration: Seamlessly integrate custom tools and APIs
• 🎯 Precise Control: Fine-grained control over agent behavior and decision-making
• 🔍 Observable: Built-in support for tracing, debugging, and monitoring
• 🚀 Production Ready: Deploy with LangGraph Cloud or self-host

• ✅ Production-Ready Agents: Fully functional, well-documented agents you can deploy today
• ✅ Best Practices: Clean code, comprehensive prompts, and robust error handling
• ✅ Real-World Use Cases: Practical agents solving actual business problems
• ✅ Educational: Learn agent architecture patterns and LangGraph concepts
• ✅ Open Source: MIT licensed - use freely in your projects

🌤️ Weather Agent Intelligent weather assistant providing forecasts and activity-based recommendations. Key Features: 🎯 Activity-based YES/NO recommendations ⏰ Time-aware forecasting (tonight, tomorrow, etc.) 📊 Comprehensive weather data (current + 7-day forecast) 🆓 Completely FREE - no weather API key needed 🤖 Claude Sonnet 4.5 powered analysis Tech Stack: LangGraph • LangChain • Anthropic • Open-Meteo View Demo | Documentation

🔍 Web Search Agent Intelligent search assistant that provides comprehensive, well-researched answers by leveraging multiple web search APIs. Key Features: 🔍 Dual search engine integration (Tavily + Google Serper) 🎯 Cross-references and validates information across sources 📊 Expert-quality responses with source attribution ⚡ Real-time information from the web 🤖 Claude Sonnet 4.5 powered synthesis Tech Stack: LangGraph • LangChain • Anthropic • Tavily • Serper View Demo | Documentation

📱 Blog to Tweet Agent Automatically converts blog posts into engaging X/Twitter threads. Key Features: 🔗 Web scraping with Firecrawl 🤖 Smart content summarization 🧵 Optimized tweet thread generation ✨ Claude Sonnet 4.5 powered Tech Stack: LangGraph • LangChain • Anthropic • Firecrawl View Demo | Documentation

🎥 YouTube Video to Blog Agent Transforms YouTube videos into SEO-friendly, well-structured Markdown blog posts. Key Features: 🎥 Automatic YouTube transcript extraction ✍️ AI-powered content generation 📝 SEO-optimized Markdown format 🎯 Complete structure (TL;DR, ToC, FAQs) 🧹 Filters out YouTube-specific filler 🤖 Claude Sonnet 4.5 powered Tech Stack: LangGraph • LangChain • Anthropic • Klavis MCP View Demo | Documentation

We're actively developing more agents! Star ⭐ this repo to stay updated.

Planned Agents:

• 📧 Email Response Agent - Intelligent email drafting and responses
• 📊 Data Analysis Agent - Automated insights from datasets
• 💬 Customer Support Agent - Multi-turn support conversations

Have an idea? Open an issue or contribute!

• Python 3.12 or higher
• uv (recommended) or pip
• API keys for the services you plan to use (Anthropic, OpenAI, etc.)

1. Clone the repository

git clone https://github.com/lokeswaran-aj/awesome-langgraph-agents.git
cd awesome-langgraph-agents

2. Choose an agent and navigate to its directory

# Weather Agent
cd agents/weather-agent

3. Install dependencies

# Using uv (recommended)
uv sync

# Or using pip
pip install -e .

4. Configure environment variables

cp .env.example .env
# Edit .env with your API keys

5. Run the agent

langgraph dev

6. Access LangGraph Studio

Open LangGraph Studio in your browser.

• LangGraph - Agent workflow orchestration
• LangChain - LLM application framework
• Anthropic Claude - Advanced AI models

• Open-Meteo - Free weather data API
• Tavily - AI-optimized search API
• Google Serper - Google search results API
• Firecrawl - Web scraping and content extraction
• Klavis - MCP Server platform for tool integration
• Python 3.12+ - Modern Python features
• uv - Fast Python package management
• LangSmith - Observability and debugging

We welcome contributions! Here's how you can help:

1. Fork the repository
2. Create a new directory under agents/your-agent-name/
3. Follow the agent template structure:

   agents/your-agent-name/
   ├── README.md              # Comprehensive documentation
   ├── langgraph.json         # LangGraph configuration
   ├── pyproject.toml         # Dependencies
   ├── .env.example           # Environment template
   ├── assets/                # Demo videos, images
   └── src/
       ├── __init__.py
       ├── agents.py          # Agent definitions
       ├── graph.py           # LangGraph workflow
       ├── model.py           # LLM configuration
       ├── prompt.py          # All prompts
       ├── state.py           # State schemas
       └── tools.py           # Custom tools
   

4. Include a demo (GIF or video)
5. Write comprehensive documentation
6. Submit a pull request

• ✅ Write clean, well-documented code
• ✅ Include comprehensive README with usage examples
• ✅ Add demo visuals (GIF/screenshots)
• ✅ Follow existing code style and structure
• ✅ Test thoroughly before submitting
• ✅ Update main README with your agent

• Use type hints
• Write descriptive docstrings
• Separate prompts into dedicated files
• Include error handling
• Provide environment templates

awesome-langgraph-agents/
├── agents/                       # Individual agent directories
│   ├── weather-agent/           # Weather & planning agent
│   │   ├── README.md
│   │   ├── src/
│   │   └── ...
│   ├── web-search-agent/        # Web search & research agent
│   │   ├── README.md
│   │   ├── src/
│   │   └── ...
│   ├── blog-to-tweet-agent/     # Blog to tweet generation agent
│   │   ├── README.md
│   │   ├── src/
│   │   └── ...
│   └── youtube-video-to-blog/   # YouTube to blog conversion agent
│       ├── README.md
│       ├── src/
│       └── ...
├── LICENSE                       # MIT License
└── README.md                     # This file

If you find this project helpful, please consider giving it a ⭐!

This project is licensed under the MIT License - see the LICENSE file for details.

• Inspired by awesome-llm-apps
• Built with LangGraph by LangChain
• Powered by Anthropic Claude
• Special thanks to Klavis for providing free MCP credits for tool integration