Skip to content
  • AI
  • Linux VPS
  • Ubuntu 24.04

Self-host Flowise on a VPS

Flowise runs well on a GhostRDP Linux VPS Basic plan with 2 vCPU and 6 GB RAM in Germany or the Netherlands, from €5.99/mo.

Flowise is an open-source, drag-and-drop builder for LLM chains, chatbots and AI agents. This guide runs it in Docker and reaches the editor privately through an SSH tunnel.

  • Visual flow builder

    Connect models, tools and data sources by drag and drop.

  • API for every flow

    Call your chatflows from your own apps.

  • Private editor

    Reach Flowise through an SSH tunnel, no open port.

Plans for Flowise

Flowise itself is light; the model providers do the heavy work. Basic is enough to start. Pick Standard if you also run a local model server or many flows at once.

  • Linux VPS Basic

    Recommended

    €5.99/mo

    €5.09/mo billed yearly, save €10/year

    • 2 vCPU
    • 6 GB ECC RAM
    • 40 GB NVMe
    • 1 Gbps port
    Order Basic
  • Linux VPS Standard

    €12.99/mo

    €11.04/mo billed yearly, save €23/year

    • 4 vCPU
    • 8 GB ECC RAM
    • 70 GB NVMe
    • 1 Gbps port
    Order Standard
  • Linux VPS Pro

    €25.99/mo

    €22.09/mo billed yearly, save €46/year

    • 6 vCPU
    • 12 GB ECC RAM
    • 90 GB NVMe
    • 1 Gbps port
    Order Pro

What you need

  • Operating system
    Linux VPS with Ubuntu 24.04
  • Minimum resources
    1 vCPU and 2 GB RAM
  • Models
    API keys for your model providers, or a local Ollama server

Official site: docs.flowiseai.com

How to install Flowise

Written for Ubuntu 24.04 from the official instructions. Run the commands as root and replace YOUR_SERVER_IP with your server's address.

  1. 1

    Connect to your server over SSH

    Use the IP address and root password from your welcome email (the server page has a Copy SSH command button). Windows 10 and 11, macOS and Linux all include an SSH client in the terminal.

    Shell
    ssh root@YOUR_SERVER_IP
  2. 2

    Update the system

    Install the latest security updates before you add anything else.

    Shell
    apt update && apt -y upgrade
  3. 3

    Install Docker

    Docker's official convenience script adds Docker's own package repository and installs Docker Engine with the Compose plugin.

    Shell
    curl -fsSL https://get.docker.com -o get-docker.sh
    sh get-docker.sh
    docker --version
  4. 4

    Start Flowise

    Runs the official flowiseai/flowise image on port 3000, listening on the server itself only, with its data in a Docker volume.

    Shell
    docker run -d --name flowise --restart unless-stopped \
      -p 127.0.0.1:3000:3000 \
      -v flowise_data:/root/.flowise \
      flowiseai/flowise
  5. 5

    Open the editor through an SSH tunnel

    Run this on your PC and keep the window open, then open http://localhost:3000 and create your account.

    Shell
    ssh -L 3000:localhost:3000 root@YOUR_SERVER_IP

After installing

  • Public chatbots
    To embed a chatbot on a website, put Flowise behind a domain with HTTPS (for example Caddy as a reverse proxy) instead of the tunnel.
  • Updating
    docker pull flowiseai/flowise, then remove and start the container again with the same command. Your data stays in the flowise_data volume.
  • Backups
    Server backups are not included. Export your flows or back up the flowise_data volume.

Flowise questions

Which plan do I need for Flowise?

Basic for Flowise with hosted model providers. Standard or Pro if you also run local models on the same server.

Can Flowise use local models?

Yes, for example through Ollama on the same server. Our servers have no GPU, so local models run on the CPU.

Why use an SSH tunnel?

It keeps the editor off the public internet without setting up a domain and certificate.

Is Flowise free to self-host?

Flowise is open source. Check the license in Flowise's repository for your use.

Stuck on a step? Our team answers on live chat and in tickets.

More on GhostRDP

Run Flowise on your own server.

Online in minutes. Pay with crypto, no ID needed.