Langflow
Langflow is an open-source platform for building and deploying AI-powered agents and workflows. It offers a visual builder, API and MCP servers, and supports major LLMs and vector databases. It is for developers who want to create AI applications quickly and integrate them into any stack.
🎬 How We Built 2 AI Agents in 8 Mins using Langflow! | No Coding Required · Builders Central by Zoho Creator
✨ Key features
- Visual builder interface for quick iteration.
- Source code access to customize components in Python.
- Interactive playground for step-by-step testing and refinement.
- Multi-agent orchestration with conversation management and retrieval.
- Deploy as an API or export as JSON.
- Deploy as an MCP server for MCP clients.
🎯 Use cases
- Build AI agents and workflows visually.
- Integrate AI workflows into applications via API or MCP.
- Customize AI components with Python.
- Test and refine flows interactively.
- Deploy AI workflows to cloud platforms.
📦 Installation
🧰 Requirements: Requires Python 3.10–3.14 and uv (recommended package manager).
Install locally (recommended)
Requires Python 3.10–3.14 and uv (recommended package manager).
Install
From a fresh directory, run:
uv pip install langflow -U
The latest Langflow package is installed. For more information, see Install and run the Langflow OSS Python package.
Run
To start Langflow, run:
uv run langflow run
Langflow starts at http://127.0.0.1:7860.
That's it! You're ready to build with Langflow! 🎉
🚀 Usage
uv run langflow run
Langflow starts at http://127.0.0.1:7860.
⚠️ Good to know
No limitations are stated in the README.
❓ FAQ
What are the system requirements to install Langflow?
You need Python 3.10–3.14 and uv (recommended package manager).
How do I start Langflow after installation?
Run uv run langflow run and it will start at http://127.0.0.1:7860.
Can I deploy Langflow as an API?
Yes, Langflow allows you to deploy your flows as an API or export them as JSON for Python apps.
Is there a desktop version available?
Yes, Langflow Desktop is available for Windows and macOS and includes all dependencies.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.