Skip to content
Get started

Flowise on a VPS

AI agent builder

Install on a VPSGitHub
Category
AI / Automation
Hosting
AI services
Author
FlowiseAI
License
Apache-2.0
Version
3.1.4

The script is free · VPS from $4.63 per month · installs in about 2 minutes

Install over SSH

root@vps:~# command -v docker >/dev/null || curl -fsSL https://get.docker.com | sh; mkdir -p /opt/flowise && chown -R 1000:1000 /opt/flowise && docker run -d --name flowise --restart unless-stopped -p 3000:3000 -v /opt/flowise:/home/node/.flowise flowiseai/flowise

  • SystemUbuntu 24.04 · x86_64ok
  • Sourcegithub.com/FlowiseAI/Flowiseok
  • Version3.1.4ok
  • Port3000/tcplisten

✓ Flowise 3.1.4 installed · about 2 minutes

root@vps:~#

Install command from the library. Output is shortened and may differ on your server.

What it is

  • AI agents
  • LLM
  • RAG
  • No-code

Flowise is a visual builder for LLM-powered AI agents and chatbots. Model, memory, vector database and tool blocks are connected on a canvas, and the finished bot is available via API or as a website widget.

Great for quickly building a support bot over your own documents (RAG) or an agent with tools, without hand-coding chains.

The core code is open source under Apache-2.0; enterprise features are under a commercial license.

  • Visual editor for chains and agents
  • RAG over your own documents
  • OpenAI, Ollama and other models
  • API and chat widget for websites
  • Vector databases: Qdrant, Pinecone, pgvector

Recommended plan

For Flowise: at least 2 vCPU, 3 GB RAM and 45 GB NVMe.

Minimum to run
1 vCPU · 2 GB RAM · 10 GB disk
Systems
Ubuntu 22.04 · Ubuntu 24.04 · Debian 12

How to install

Three steps in the bot or one command over SSH; installation takes about 2 minutes.

  1. 01

    Choose a plan in the bot

    Open @ExpressHost_bot and pay for a VPS. The server will be ready in about 60 seconds.

  2. 02

    Add Flowise

    At the “Add-ons” step pick the script from the library, or run it later: Server settings → Scripts.

  3. 03

    Open http://SERVER-IP:3000 and create an administrator account

    The bot will send the server address and login details to the chat.

Manually over SSH

Connect to the server as root and run the command. Supported systems: Ubuntu 22.04, Ubuntu 24.04, Debian 12.

Install command
command -v docker >/dev/null || curl -fsSL https://get.docker.com | sh; mkdir -p /opt/flowise && chown -R 1000:1000 /opt/flowise && docker run -d --name flowise --restart unless-stopped -p 3000:3000 -v /opt/flowise:/home/node/.flowise flowiseai/flowise

Ports

Flowise ports
PortProtocolPurpose
3000tcpWeb interface and API

After installation

  1. 1.Open http://SERVER-IP:3000 and create an administrator account
  2. 2.Add a model key in Credentials and build your first chatflow
  3. 3.For access via a domain, set up an HTTPS proxy to port 3000

Flowise FAQ

Didn’t find an answer? Message @ExpressHost_SupportBot.

Port 3000 is already in use. What should I do?

Publish on a different port, for example -p 3001:3000. Open WebUI and Grafana use the same port by default.

How do I update Flowise?

Run docker pull flowiseai/flowise and recreate the container with the same command. Your data stays in /opt/flowise.

Flowise or n8n?

Flowise is built for LLM chains and agents. n8n is general-purpose automation with hundreds of integrations, where AI is just one of the features.

Flowise installs at checkout — in the bot.

Install FlowiseBuy in Telegram