HomeTemplates › Langflow
🔀 Agents & Workflows

Langflow: agents built on a canvas

Visual LangChain: drag, connect and publish flows as API

From
loading…
cheapest machine that meets this template
Deploy in one click →
Video memory
4 GB
Setup
~4 min
Access
port 7860
Billing
hourly, in BRL

Langflow turns what would be orchestration code into blocks wired on a canvas. You build the flow, test it right there and publish it as an API — without writing the glue between model, vector store and tools.

Langflow is a visual IDE for LangChain. Build RAG, agents, chatbots and pipelines by dragging blocks: LLMs (OpenAI, Anthropic, local vLLM), vector stores, tools and memory. Export each flow as a REST endpoint.

What it is for

How to deploy

  1. Create your account and add balance (card or Pix, no subscription).
  2. In the console, pick the Langflow template and a machine — the console hides the ones that do not meet the requirement.
  3. In about 4 minutes the setup finishes and the access address shows up in the panel, on port 7860.

Done? Just destroy the machine and billing stops with it. No contract, no minimum commitment.

FAQ

Does it need a GPU?

Only if the model runs on the same machine. Pointing at an external API, a small machine is enough.

Can I export the flow?

Yes, as JSON, so you can version it in your repository.

Is it production-ready?

It is fine for prototyping and moderate load; high volume calls for your own code.

Run Langflow today
You only pay for the hours the machine is running.
Deploy in one click →

Related templates

browser-use
An agent that drives the browser on its own — local model, no API key
AutoGen Studio
AI agent teams that collaborate — by Microsoft
n8n
Visual automation with 400+ integrations + AI nodes