Skip to content

Langflow

by LangflowAppGet organised

Lets you build AI agents and workflows by connecting blocks on a visual canvas

View on GitHub

About Langflow

Langflow is a visual builder for AI agents and workflows: you connect components on a canvas, test them in a playground and run the result as an API or an MCP server.

For DevelopersBuilders of agentic and RAG apps

Made by Langflow

Langflow is an open-source project from the langflow-ai organization on GitHub. Its website describes it as a low-code AI builder for agentic and RAG applications.

Stars
★ 156k
License
MIT
Cost
Usage-based
Platforms
Mac · Win · Linux
Runs
Local · Self-hosted

Screenshots

From the project's own repository · 3 images, swipe or use the arrows.

The Langflow workspace: an empty canvas with a list of components on the left
The Langflow playground, a chat window for testing a flow
A simple agent flow built from connected components on the Langflow canvas
Image: Langflow (MIT). Original file

Overview

Langflow is a visual builder for AI agents and workflows. You connect components on a canvas, test the flow in a built-in playground, and then run it as an API or as an MCP server that other tools can call. It comes as a desktop app for macOS and Windows, a Docker image or a Python package, and any component can be edited in Python. It suits people who want to build an agent without writing a whole app first.

Every step of an agent is a block you can see and change, and a finished flow becomes an API or an MCP tool.

Try these first

Start with the first one: it is a small task you can check easily.

  1. Introduce yourself in one sentence.First try · playground chat

  2. Summarize this text in three bullet points: [paste text]

  3. Answer only from the document I uploaded: [your question]reads your file

  4. Explain what each step of this flow does, in plain words.

Example prompts written by Agent Flows Hub.

Features

From the creator's documentation.

FeatureWhat it doesRuns
Visual builderConnect components on a canvas to build agents and flowsYour computer
PlaygroundTest a flow in a chat window with step-by-step controlYour computer
Custom componentsEdit the Python source code of any componentYour computer
API and MCPRun a flow as an API endpoint or as an MCP server for other toolsYour network
Model providersConnects to the major language models and vector databasesModel provider's API
Desktop appA standalone app for macOS and Windows that manages its own dependenciesYour computer

Good to know

You want to try an agent idea without building an app first. In Langflow you lay out the steps on a canvas, run them in the playground and see what each block does, then expose the flow as an API or an MCP tool.

Limits

  • Langflow Desktop leaves out some features, including the Shareable Playground and Voice Mode, and the Windows installer may ask you to install Microsoft C++ Build Tools.
  • Official release packages and Docker images require a superuser password: set LANGFLOW_SUPERUSER_PASSWORD before you start the server.

Notes by (original project name: Langflow), written from the creator's documentation, not from running it ourselves. Install Langflow · Langflow README · Langflow Desktop download page · Langflow Quickstart

Stuck setting it up?

Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.

Get help

Other apps

  • LearnHarness Teaches you a hard topic step by step, starting from what you already understand
  • LibreChat Gives you a self-hosted ChatGPT-style app where you switch between many AI models
  • LM Studio Finds, downloads and runs open AI models on your computer in one desktop app
  • LobeHub Lets you build a team of AI agents that chat, write and run scheduled tasks for you
  • LocalMiniDrama Turns a story idea into a script, storyboard and finished short drama video on your PC
  • Macro Puts your team's email, chat, tasks, docs and AI agents in one linked workspace

See all 122 apps · When a setup fails

GitHub