// automation · langflow-ai/langflow

Langflow

Langflow is an open-source automation project by langflow-ai (langflow-ai/langflow on GitHub). It has 155,769 GitHub stars and 10,241 forks, is released under the MIT license, and was last updated on GitHub on 17 October 2026.

Langflow — the visual builder for AI agents and workflows: drag-and-drop flows over LangChain components, deployed as APIs or MCP tools, MIT-licensed

★ 155.8k stars⑂ 10.2k forksMITupdated 2026-10

View on GitHub ↗Official site ↗

▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.

// project facts

Project facts

Repository: langflow-ai/langflow
GitHub stars: 155,769
Forks: 10,241
License: MIT
Last updated on GitHub: 17 October 2026
Category: Automation
Listing: Full install guide
Official site: Official site

// how it works

How it works

Install Langflow
Install it into a fresh environment with uv, per the README: uv pip install langflow -U (Python 3.10–3.13).
Start the builder
Run uv run langflow run and open http://127.0.0.1:7860 — the visual editor, playground and component library are all in the browser.
Build, then deploy the flow
Drag components into a flow, test it in the playground, then call it through the generated API endpoint or publish it as an MCP server.

// features

Why people love it

Visual flow building

Agents and RAG pipelines composed on a canvas from prebuilt components — prompts, models, tools, vector stores — each editable down to the Python.

Deploy as API or MCP

A finished flow becomes a REST endpoint, or an MCP server that other agents and tools can invoke directly.

Multi-agent orchestration

Flows can coordinate several specialised agents, with a playground for tracing each step before anything ships.

LangChain underneath

The component ecosystem is LangChain-based, so mainstream models, embeddings and retrievers are available without glue code.

// run it

Run it yourself

Install with uv
The README install path: uv is the recommended installer.
```
uv pip install langflow -U
uv run langflow run
```

Run with Docker

The official image, with an admin password set at first run.

read -rsp "Langflow administrator password: " LANGFLOW_SUPERUSER_PASSWORD; echo
export LANGFLOW_SUPERUSER_PASSWORD
docker run -p 7860:7860 -e LANGFLOW_SUPERUSER_PASSWORD langflowai/langflow:latest

Open the editor
Once it starts, the whole builder runs in the browser.
```
http://127.0.0.1:7860
```

// use cases

What you can build

Prototyping an AI agent visually before committing to a code-only framework
Shipping RAG and chatbot flows as APIs without writing the serving layer
Exposing internal tools to other agents through MCP
Teaching or demoing how LLM pipelines fit together, component by component

Automation is not only pipelines. PennyWise AI Tracker automatically reads the transaction SMS messages your bank sends and turns them into a trackable expense record, and Well promises the same spirit for household finance — "no more Sundays on Finance." Also on this shelf: bricks — Local, open-source Clay alternative for AI lead enrichment.

// faq

Questions, answered

Who makes Langflow?

The Langflow open-source project (langflow-ai on GitHub); it grew out of the Logspace team and is now stewarded with backing from DataStax/IBM.

Is Langflow free?

Yes — MIT licensed and fully self-hostable. You pay only for your own infrastructure and any model API keys you plug in.

Do I need to code?

No for standard flows — the builder is visual. Custom components are Python, and every built-in component can be opened and edited when you outgrow the defaults.

How does it compare to a well-known alternative?

Against n8n, Langflow is AI-first: its canvas is built around models, prompts and agents rather than app integrations. Against code frameworks like LangChain itself, it trades some flexibility for a visual builder and one-click API/MCP deployment.

How do I get started?

The most-starred other Automation projects in the LibreAI catalogue — the realistic shortlist if Langflow is not the right fit.

n8n★ 206.6k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+…
awesome-claude-skills★ 76.4k
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Flowise★ 55.5k
Flowise — build AI agents visually: an open-source drag-and-drop UI over LangChain and LlamaIndex, with chatflows, agentflows and a marketplace of templates
Huginn★ 50.0k
Create agents that monitor and act on your behalf. Your agents are standing by!
airflow★ 47.0k
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

// more in automation

Get Langflow

Free and open — grab the source, star the repo, and start creating.

View on GitHub ↗← More Automation tools

Langflow

Project facts

How it works

Why people love it

Visual flow building

Deploy as API or MCP

Multi-agent orchestration

LangChain underneath

Run it yourself

What you can build

Questions, answered

Similar tools

Flowise

ai-flow

Activepieces

workflowbuilder

ghost-os

AutomationBench

Alternatives in Automation

More in Automation

Get Langflow