FastAPI LangGraph Chatbot
A scalable AI chatbot platform built with FastAPI and LangGraph, featuring multi-agent orchestration, multi-tenant vector storage, cross-chat memory, and voice call capabilities through LiveKit integration.
What is FastAPI LangGraph Chatbot?
FastAPI LangGraph Chatbot is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to scalable ai chatbot platform built with fastapi and langgraph, featuring multi-agent orchestration, multi-tenant vector storage, cross-chat memory, and voice call capabilities through livekit integrat...
A scalable AI chatbot platform built with FastAPI and LangGraph, featuring multi-agent orchestration, multi-tenant vector storage, cross-chat memory, and voice call capabilities through LiveKit integration.
This server falls under the Coding Agents and Communication categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A scalable AI chatbot platform built with FastAPI and LangGr
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx fastapi-langgraph-chatbot-with-vector-store-memory-mcp-tools-and-voice-modeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use FastAPI LangGraph Chatbot
This project is a full-stack AI chatbot platform that combines FastAPI for the backend API, LangGraph for multi-agent orchestration, Qdrant for multi-tenant vector storage and cross-chat memory, and LiveKit for real-time voice call capabilities. It integrates MCP-compatible tools (Firecrawl for web scraping and Tavily for semantic search) so agents can retrieve live information while maintaining long-term conversational context via Mem0. Teams that need a scalable, production-ready chatbot infrastructure with persistent memory and voice support will find it a comprehensive starting point.
Prerequisites
- Python 3.10 or later with pip and venv
- Docker (recommended for running Qdrant vector database locally)
- OpenAI API key (or compatible LLM provider key)
- LiveKit account and credentials (LIVEKIT_URL, LIVEKIT_API_KEY, LIVEKIT_API_SECRET) for voice mode
- Firecrawl and Tavily API keys for web scraping and search tools
Clone the repository and set up the Python environment
Clone the project from GitHub, create a virtual environment, and install all required Python dependencies.
git clone https://github.com/extrawest/fastapi-langgraph-chatbot-with-vector-store-memory-mcp-tools-and-voice-mode.git
cd fastapi-langgraph-chatbot-with-vector-store-memory-mcp-tools-and-voice-mode
python -m venv venv
source venv/bin/activate
pip install -r requirements.txtStart Qdrant vector database
Run Qdrant locally using Docker. The chatbot uses Qdrant for multi-tenant vector storage to power semantic search over conversation history.
docker run -p 6333:6333 qdrant/qdrantConfigure environment variables
Copy the example .env file and fill in your credentials. At minimum you need an OpenAI API key, Qdrant host/port, and LiveKit credentials for voice mode.
cp .env.example .env
# Then edit .env with your values:
# OPENAI_API_KEY=sk-...
# QDRANT_HOST=localhost
# QDRANT_PORT=6333
# LIVEKIT_URL=wss://...
# LIVEKIT_API_KEY=...
# LIVEKIT_API_SECRET=...
# SECRET_KEY=your-secret-key
# ACCESS_TOKEN_EXPIRE_MINUTES=60
# SQLALCHEMY_DATABASE_URI=sqlite:///./chatbot.dbStart the FastAPI server
Run the FastAPI application. The API will be available at http://localhost:8000, with interactive docs at /docs.
uvicorn main:app --reload --port 8000Interact via the API or integrate with an MCP client
Send chat requests to the /chat endpoint. The multi-agent system (supervisor, research, and scraper agents) will handle your queries, persist context in Qdrant via Mem0, and invoke Firecrawl or Tavily tools as needed.
curl -X POST http://localhost:8000/chat \
-H 'Content-Type: application/json' \
-d '{"message": "What are the latest AI news?", "session_id": "user-123"}'FastAPI LangGraph Chatbot Examples
Client configuration
Environment variables needed in the .env file to run the FastAPI LangGraph chatbot with all features enabled.
{
"OPENAI_API_KEY": "sk-...",
"QDRANT_HOST": "localhost",
"QDRANT_PORT": "6333",
"LIVEKIT_URL": "wss://your-livekit-server",
"LIVEKIT_API_KEY": "your-livekit-api-key",
"LIVEKIT_API_SECRET": "your-livekit-api-secret",
"SECRET_KEY": "your-jwt-secret",
"ACCESS_TOKEN_EXPIRE_MINUTES": "60",
"SQLALCHEMY_DATABASE_URI": "sqlite:///./chatbot.db",
"LANGCHAIN_TRACING_V2": "true",
"LANGSMITH_API_KEY": "your-langsmith-key"
}Prompts to try
Example questions and tasks you can send to the chatbot API to exercise different agents and tools.
- "What are the latest developments in AI this week?"
- "Summarize the content at https://example.com/article"
- "What did we discuss last time about my project?"
- "Start a voice call session to walk me through the setup steps"
- "Search for Python tutorials on async programming"Troubleshooting FastAPI LangGraph Chatbot
Qdrant connection errors on startup
Ensure Qdrant is running on the host and port specified in QDRANT_HOST and QDRANT_PORT. Run 'docker ps' to verify the Qdrant container is active and the port 6333 is exposed.
Voice mode fails to connect
Double-check that LIVEKIT_URL, LIVEKIT_API_KEY, and LIVEKIT_API_SECRET are set correctly in .env. The LiveKit URL must start with 'wss://' and point to your LiveKit cloud or self-hosted server.
Agent does not use web search or scraping tools
Ensure OPENAI_API_KEY is valid and that Firecrawl and Tavily API keys are configured in .env. LangGraph tool invocation depends on the LLM correctly selecting tools, so verify LANGCHAIN_TRACING_V2 is enabled to debug agent decisions.
Frequently Asked Questions about FastAPI LangGraph Chatbot
What is FastAPI LangGraph Chatbot?
FastAPI LangGraph Chatbot is a Model Context Protocol (MCP) server that scalable ai chatbot platform built with fastapi and langgraph, featuring multi-agent orchestration, multi-tenant vector storage, cross-chat memory, and voice call capabilities through livekit integration. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install FastAPI LangGraph Chatbot?
Follow the installation instructions on the FastAPI LangGraph Chatbot GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with FastAPI LangGraph Chatbot?
FastAPI LangGraph Chatbot works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is FastAPI LangGraph Chatbot free to use?
Yes, FastAPI LangGraph Chatbot is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
FastAPI LangGraph Chatbot Alternatives — Similar Coding Agents Servers
Looking for alternatives to FastAPI LangGraph Chatbot? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up FastAPI LangGraph Chatbot in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use FastAPI LangGraph Chatbot?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.