← Discover
GitHub · langflow-ai/langflow↑ +117 today

AI workflows with visual interface

Langflow is a Python-based development platform that offers a visual interface for building AI-powered agents and workflows. Users can design and deploy complex language model applications using drag-and-drop without writing code.

Updates

  • November 4, 2026: Stars 155,949 → 156,307, latest release v1.13.1 (November 4, 2026).
  • October 23, 2026: Stars 155,880 → 155,949, latest release v1.13.0 (October 22, 2026).
  • October 21, 2026: Stars 155,615 → 155,880, latest release v1.12.7 (October 21, 2026).
  • October 13, 2026: Stars 155,555 → 155,615, latest release v1.12.6 (October 13, 2026).

What you get

  • Designing AI agents using drag and drop
  • Publishing workflows as API or MCP server
  • Integration with large language models and vector databases

Installation

Using pip (PyPI)
pip install langflow

Running it

Launch Langflow UI
langflow run

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to create an artificial intelligence agent using Langflow. Guide me in designing a basic language model flow using the visual interface. Explain step by step which components I need to drag, how to connect these components together, and how I can export the flow I created as an API.

Repository: https://github.com/langflow-ai/langflow. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

MCPAPIArtificial Intelligence
Who it is forIt is for users who want to develop complex AI applications and agent workflows without writing code.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-03: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.