Skip to content

Flowise

AI Platform & Data Flowise 3.1.4 Hardened AMI

Flowise 3.1.4 on Ubuntu 24.04 LTS, ready to run on your own EC2 instance. Flowise is a drag-and-drop builder for LLM chatbots, RAG pipelines and AI agents: connect nodes for models, prompts, document loaders, vector stores and tools, test the flow in your browser, then call it over an API. Nothing listens on a public interface: you open the builder over HTTPS through AWS Systems Manager port forwarding. This page covers what is on the image, the defaults it ships with and how billing works.

AMI release
0.1.15 (Flowise 3.1.4)
Recommended
t3.medium
Storage
32 GiB+ encrypted gp3
Access
Web UI in your browser
Released
Oct 12, 2026
Delivery
Amazon Machine Image in your own AWS account

Build LLM chatbots, RAG pipelines and agent flows visually, then call them through the Flowise API.

Loopback-only HTTPS UI with a per-instance certificate and an owner password generated on first boot, reached through Session Manager port forwarding.

Runs in your AWS account with local SQLite storage. Connect the model providers you already use, including Amazon Bedrock.

Quick start

Full guide →
  1. Subscribe
  2. Launch the instance
  3. Connect and run the walkthrough
  4. Get the owner password
  5. Open the builder
  6. Connect a model and build a flow

What is on the image

  • Flowise 3.1.4, installed from the pinned npm release in /opt/flowise, with a pinned Node.js 22 runtime in /opt/sushi/node.
  • SQLite storage for flows, credentials and settings in /var/lib/flowise/.
  • nginx as a loopback HTTPS proxy in front of Flowise.
  • systemd services: flowise runs Flowise as the unprivileged flowise user, and nginx serves HTTPS.
  • Per-instance identity. First boot creates this instance's TLS certificate and a random password for the owner account admin@localhost.local. The image contains no password, certificate, database or provider keys.
  • A walkthrough script, /opt/sushi/docs/demo.sh, that checks the installation for you.

Not included: model-provider credentials, Docker, Chromium or Playwright browsers, Redis queue workers and Postgres. Upstream enterprise features are not licensed by this offer.

Ports

Port Protocol Listens on Purpose
8443 HTTPS 127.0.0.1, [::1] Flowise UI and API, through nginx
3000 HTTP 127.0.0.1 Flowise itself. Leave it on loopback.

No inbound security group rule is needed. You reach the UI with Session Manager port forwarding.

t3.medium (4 GiB of memory) with an encrypted gp3 root volume of at least 32 GiB and IMDSv2. The instance needs outbound HTTPS to reach your model providers.

Billing

You pay an hourly software fee while the instance runs, as shown in the offer terms on the listing, which also shows any free trial. AWS bills EC2, EBS and data transfer separately. Your model providers bill their own usage.

Where to go next

Upstream project

Flowise is developed by FlowiseAI. The open-source core is published under the Apache-2.0 license; enterprise portions carry FlowiseAI commercial terms. See the Flowise documentation for nodes, flows, credentials and the API. Software Sushi packages the image; FlowiseAI does not endorse it, and its support is not included.

Last updated October 13, 2026 · Suggest an improvement