Skip to content
Get packs

Langflow

Visual builder for creating and deploying AI agents and workflows, with API and MCP server output.

GitHub Download v1.13.0
Stars
156k
Forks
10.3k
Licence
MIT
Language
Python
Last update
4 days ago
Type
App

What it is

Langflow is a platform for building AI-powered agents and workflows. It offers a visual editor for assembling flows, and each finished workflow can be exposed as an API or as an MCP server so other applications and tools can use it. The README says it supports major LLMs, vector databases, and a range of AI tools.

  • Build a visual flow that connects an LLM to a vector database for document question answering
  • Test and step through a multi-agent flow in the built-in playground
  • Export a finished flow as JSON or deploy it as an API for a Python app
  • Turn a workflow into an MCP server so MCP clients can call it as a tool

Great for

  • Developers who want a visual way to prototype LLM workflows and then move them into code
  • Teams building multi-agent or retrieval-based assistants
  • People who want to expose a workflow as an API or MCP tool for other apps
  • Users who prefer a desktop installer, which the README says exists for Windows and macOS

Not ideal for

  • People who need a simple chat app with no setup, since it is a broader platform with many components to configure
  • Anyone deploying to a public server without planning authentication, because the README says auto-login is disabled in official releases and a password must be set
  • Users on Python versions outside 3.10–3.14, as the README lists that range as required
Step-by-step guide: how to use LangflowInstall, first run, examples, tips and FAQs
Langflow vs LlamaIndex

How to get it

  1. 1

    Install with a package manager

    You'll need: Python 3.10–3.14 · uv (recommended package manager)

    Install Langflow

    uv pip install langflow -U

    Start Langflow (set LANGFLOW_SUPERUSER_PASSWORD first)

    uv run langflow run
  2. 2

    Run it

    • Install Python 3.10–3.14 and uv
    • Run uv pip install langflow -U from a fresh directory
    • Set LANGFLOW_SUPERUSER_PASSWORD in your environment
    • Run uv run langflow run
    • Open http://127.0.0.1:7860 and sign in as langflow
  3. 3

    Get the most out of it

    • Enable authentication and use API keys when exposing flows to other apps, as described in the authentication docs linked in the README
    • Use the interactive playground to test and refine flows step by step before deploying
    • Customize components with Python source code access when the built-in components do not fit
    • Add observability through integrations the README mentions, such as LangSmith or LangFuse
    • Follow the linked deployment guides to run it on a major cloud

Downloads

Source code (.zip)main branch · straight from GitHubRelease v1.13.02 files incl. langflow-1.13.0-py3-none-any.whlOfficial website & docswww.langflow.org

Strengths

  • Visual builder combined with source code access to customize components in Python
  • Flows can be deployed as APIs or MCP servers, not just used in the editor
  • Open source under the MIT license with a large community around it

Trade-offs

  • The README is truncated and gives limited detail on configuration, so setup for production use requires reading the linked docs
  • Running it safely requires setting an administrator password, which adds a step for newcomers
  • Its scope is broad, so there is a learning curve to understand components, flows, and deployment options

How it compares

ProjectStarsTypeLevelUpdatedBest for
langflow (this)156kAppintermediate4 days agoDevelopers who want a visual way to prototype LLM workflows and then move them into code
llama_index52.8kLibraryintermediate10 days agoPython developers building retrieval-augmented generation (RAG) apps over private documents
langgraph44.3kLibraryintermediate4 days agoPython developers building multi-step AI agents that must survive failures or long waits
Prompt-Engineering-Guide79.8kLearning resourcebeginner8 months agoPeople who are new to prompting and want structured lessons with examples
langchain149kFrameworkintermediate4 days agoPython developers building LLM-powered applications
repomix29.1kCLIbeginner4 days agoDevelopers who want to ask an AI assistant questions about a whole project

Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.