Open-source visual builder for LLM agents, RAG pipelines and MCP servers, backed by DataStax and IBM. MIT-licensed with no artificial feature gating

Overview

Langflow is a drag-and-drop canvas for building LLM applications that compiles down to real Python. You wire together components - model calls, retrievers, vector stores, memory, tools, conditional routing - and Langflow exposes the finished graph as an API endpoint or an MCP server. It began in 2023 as a LangChain visual layer, was acquired by DataStax in 2024, and is now framework-agnostic: the LangChain dependency is optional rather than structural. The project carries an MIT license and over 150,000 GitHub stars, and ships a packaged desktop app for macOS and Windows that spares you the usual Python environment wrangling. Two things separate it from other visual builders. First, bi-directional MCP support - a Langflow flow can both consume MCP servers and be published as one, which is unusual since most builders are clients only. Second, an inline custom-component escape hatch, so you can drop raw Python into a node instead of hitting a wall when the visual paradigm runs out. The honest limitation is scale: flows get hard to read past roughly 30 nodes, version control is JSON export rather than git-native diffs, and community component quality varies. Treat it as a prototyping and internal-tools platform, not a production application framework.

Key Features

  • Visual drag-and-drop canvas with 200+ prebuilt components
  • Bi-directional MCP: consume MCP servers and publish flows as MCP servers
  • Every flow exposed as a REST API endpoint out of the box
  • Inline custom Python components when the visual layer runs out
  • Native RAG and Graph RAG retrieval pipelines
  • MIT-licensed and self-hostable via pip or Docker
  • Free desktop app for macOS and Windows with dependencies bundled

Pricing

PlanPriceFor
Open Source$0 (MIT)Self-hosters, full feature access
Langflow Desktop$0Local prototyping on Mac and Windows
Self-hosted VM~$20-100/mo infrastructureSolo devs and small production flows
EnterpriseCustom (DataStax / IBM)HA clusters, managed DB, compliance

Comparison

Compared to Flowise, Langflow’s Python-native components and MCP publishing give it more reach, while Flowise stays lighter and faster to deploy for simple chatbots. Compared to Dify, Langflow is the developer’s tool - Dify ships a fuller ops layer with datasets, annotation and usage analytics, whereas Langflow assumes you bring your own observability. n8n is the better pick when the workflow is mostly SaaS plumbing with one LLM step; Langflow wins when the LLM graph itself is the product. Budget accordingly: the software is free, but you still pay for hosting and model tokens.

Compare alternatives

Side-by-side with the 3 closest alternatives.

ToolCategoryPricingVisit
Langflow (this) agents, code, productivityFrom $0/mo Site ↗
Flowiseagents, codeFrom $0/mo Site ↗
Difyagents, productivityFrom $0/mo Site ↗
n8nagents, productivity, codeFrom $0/mo Site ↗
Langflow Current

Open-source visual builder for LLM agents, RAG pipelines and MCP servers, backed by DataStax and IBM. MIT-licensed with no artificial feature gating

agentscodeproductivity
From $0/mo

An open-source low-code platform to build LLM apps and agents as visual flows. Drag-and-drop LLM flows Read our hands-on review and compare the top AI

agentscode
From $0/mo

Open-source LLM app and agent platform with a visual workflow canvas, RAG pipelines, and one-click cloud or self-hosted deployment.

agentsproductivity
From $0/mo

Source-available workflow automation platform for building AI agents and app integrations with a visual editor. Self-hostable and source-available, so you

agentsproductivitycode
From $0/mo
Editor’s Review
4.2/5
Pros
  • +MIT-licensed with no artificial feature gating between the open-source build and paid tiers
  • +Bi-directional MCP support - a flow can be published as an MCP server, not just consume one
  • +Inline custom Python components mean you are never trapped inside the visual paradigm
Cons
  • Flows become hard to read and refactor beyond roughly 30 nodes
  • Versioning is JSON export rather than git-friendly diffs
  • Built-in observability is thin; expect to bolt on Langfuse or an equivalent

Langflow is the fastest way to get a working agent graph in front of non-engineering stakeholders, and its MCP publishing is genuinely ahead of most rivals. It starts to creak once flows grow large or need real version control, so plan on eventually exporting the logic to code.

See all reviews →

Last updated: 2026-08-04

When to use it

  • Use it when you need mIT-licensed with no artificial feature gating between the open-source build and paid tiers
  • Use it when you need bi-directional MCP support - a flow can be published as an MCP server, not just consume one
  • Use it when you need inline custom Python components mean you are never trapped inside the visual paradigm

When to skip it

  • Avoid it if flows become hard to read and refactor beyond roughly 30 nodes
  • Avoid it if versioning is JSON export rather than git-friendly diffs
  • Avoid it if built-in observability is thin; expect to bolt on Langfuse or an equivalent

Alternatives to consider