Langflow

by Langflow (DataStax / IBM)

Visually assemble agents and RAG pipelines, then ship them as APIs.

155.5 k stars GitHub MIT FreeLocalOpen source

View on GitHub →

What it does

Block-based editor for agents, RAG and multi-agent setups
Every flow becomes an API or an MCP server
Works with local (Ollama) and cloud models

Install it

Requirements: Python 3.10+ and uv (or Docker)

Install Langflow

uv pip install langflow -U

Run it

uv run langflow run

Open http://localhost:7860 in your browser

http://localhost:7860

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install Langflow (https://www.langflow.org) on my machine.
1. Check the requirements: Python 3.10+ and uv (or Docker). If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install Langflow: uv pip install langflow -U
- Run it: uv run langflow run
- see http://localhost:7860
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.