Skip to content

Langflow

AI Platform & Data Langflow 1.13.0 Hardened AMI

Langflow 1.13.0 on Ubuntu 24.04 is a visual editor for AI workflows. Package 0.2.1 creates an administrator login on first boot, stores flows in SQLite, and includes a local demo that does not call a model provider. You can also attach an OpenAI-compatible provider after launch.

AMI release
0.2.2 (Langflow 1.13.0)
Recommended
t3.large
Storage
32 GiB+ encrypted gp3
Access
Session Manager or SSH
Released
Oct 29, 2026
Delivery
Amazon Machine Image in your own AWS account

Langflow 1.13.0 visual editor with a saved input-to-model-to-output workflow and a real-provider CLI demo.

Unique first-boot administrator credentials, authenticated tunnel access and persistent single-instance SQLite storage.

Bring your own OpenAI-compatible model provider; software, infrastructure and provider charges are separate.

Quick start

Full guide →
  1. Subscribe
  2. Launch the instance
  3. Connect
  4. Sign in
  5. Run the local demo
  6. Use your own provider

What is on the image

This guide matches Marketplace package 0.2.1 (Langflow 1.13.0). Check the listing for the version currently on offer.

  • Langflow 1.13.0, started automatically by langflow.service.
  • An administrator account in /etc/langflow/admin.json. Signup and automatic login are off.
  • SQLite at /var/lib/langflow/langflow.db, one worker, one instance.
  • A local demo, bash /opt/sushi/docs/demo.sh with no arguments. It saves a Chat Input to Chat Output flow, runs it, and reads it back. It does not use a provider key.
  • A provider demo, sushi-langflow demo, with --model and --api-key-file.
  • Image notes at /opt/sushi/docs/README.md and /opt/sushi/docs/DEMO.md. Sources are under /opt/langflow/sources. Notices are under /usr/share/doc/langflow.

The editor listens on 127.0.0.1:7860. Custom component uploads, component-path overrides, and code interpreter components are disabled. SSRF protection is on. The hostname allowlist is empty until you set one.

t3.large (8 GiB of memory), Ubuntu 24.04 x86_64, with an encrypted gp3 root volume of at least 32 GiB and IMDSv2. Allow several minutes for first boot. Allow outbound access to the model provider you select. The image does not include a model subscription, API key, weights, or credits.

Billing

The listing states a software rate of USD 0.03 per running instance-hour. Confirm the offer before you subscribe. EC2, EBS, data transfer, and model-provider calls are billed separately.

Tutorial

Watch on YouTube.

Where to go next

Upstream project

Langflow is MIT-licensed. Dependencies keep their own license terms. Software Sushi packages this image and does not claim upstream or AWS endorsement.

The Langflow documentation describes the upstream project, including components this image disables. For this package, use these pages and /opt/sushi/docs/README.md on the instance.

Last updated November 1, 2026 · Suggest an improvement