LLM Deploy
langflow-ai/langflow
langflow-ai/langflow· Python
Visual drag-and-drop builder for LangChain/LangGraph agents and RAG workflows.
GitHub stats
- Stars
- 147,509
- Forks
- 8,873
- Watchers
- 467
- Open issues
- 951
meta
- License
- MIT
- Primary language
- Python
- Last commit
- 2026-04-29
- Stats fetched at
- 2026-04-29
Langflow is an open-source visual editor (now under DataStax/IBM) for composing LLM agents, RAG pipelines, and multi-agent workflows on a React Flow canvas. Each node maps to a LangChain/LangGraph component — models, vector stores, tools, prompts — and flows can be exported as Python code or served as an API. Install via `pip install langflow` or `uv pip install langflow`, then run `langflow run` to launch the local UI.
Editor's verdict
Pick Langflow when non-engineers on your team need to prototype agents visually, or when you want a quick way to demo a RAG flow without writing boilerplate. It's the most mature visual layer over LangChain — broader than Flowise on agent features, more code-friendly than n8n. Skip it if your production stack is already pure-code LangGraph or LlamaIndex; the abstraction adds debugging pain, and complex flows still end up needing custom Python nodes.