Langflow

Active
GitHub Python MIT

Description

Langflow is a visual AI agent and workflow builder platform with drag-and-drop design, multi-LLM integration, and tool composition to simplify agent development.

Key Features

  • Visual drag-and-drop builder - Graphical interface to build AI agents and workflows by dragging components
  • Multi-agent orchestration - Complex flow design with multi-agent collaboration, conversation management, and retrieval
  • API and MCP server deployment - Deploy any workflow as a REST API or MCP tool server with one click
  • Fully customizable source code - All components support Python source-level customization without limits
  • Major LLM and vector DB integration - Supports all major LLMs and vector databases out of the box
  • Observability integration - Built-in LangSmith, LangFuse, and other monitoring for debugging and performance tracking

Use Cases

💡 Rapidly prototype AI applications by dragging and combining LLM, vector DB, and tool nodes to validate ideas
💡 Build RAG workflows connecting enterprise document stores to LLMs for intelligent Q&A systems
💡 Deploy finished agent workflows as APIs for frontend apps or third-party system integration
💡 Expose Langflow workflows as MCP tools for direct invocation by MCP clients like Claude

Quick Start

# Install with uv (recommended, requires Python 3.10-3.13)
uv pip install langflow -U

# Start Langflow
uv run langflow run

# Or use Docker
docker run -p 7860:7860 langflowai/langflow:latest

# Open http://127.0.0.1:7860 in your browser to start building

Related Projects