Skip to content
Langflow AI Workflow Builder product logo
  • AWSAvailable on Amazon Web Services
  • Azure· soonComing soon on Microsoft Azure
  • GCP· nextGoogle Cloud is next on the roadmap
Available

Langflow AI Workflow Builder

Langflow 1.13.0 with PostgreSQL 16, nginx with HTTPS and Webmin on Ubuntu 24.04 LTS. Design AI agents, chatbots and RAG pipelines by connecting models, prompts, vector stores and tools on a visual canvas, test them in the built-in playground and call every flow through its own REST API. Bring your own model provider key: OpenAI, Anthropic, Amazon Bedrock, Ollama and many others. Sign-in is required, with auto-login and public sign-up turned off.

Version
v1.13.0
Operating system
Ubuntu 24.04 LTS
Architecture
x86_64
Support
Email support

What's installed

Every package and version on the image. Nothing else is installed.

  • Langflow 1.13.0
  • Python 3.12.3
  • PostgreSQL 16.15
  • nginx 1.24.0
  • Webmin 2.670

LicensingOpen source (MIT), no licence key required

Deploy anywhere

Langflow AI Workflow Builder on AWS.

Google Cloud is next on the roadmap. One clean-room build, one first-boot credential model, one patch cadence — identical on every cloud you run. Every identifier below is the real one; copy it and launch.

  1. AWS

    Amazon Web Services

    AMI · v1.13.0

    Available
    AWS AMI ID

    Shown for your region on the AWS Marketplace launch page once you subscribe.

    Released
    Root volume
    gp3 · 40 GiB
    Instance types
    • t3.large
    • t3a.large
    • t3.xlarge
    • m6a.large
    Regions34 regions· show all
    • us-east-1
    • af-south-1
    • ap-east-1
    • ap-east-2
    • ap-northeast-1
    • ap-northeast-2
    • ap-northeast-3
    • ap-south-1
    • ap-south-2
    • ap-southeast-1
    • ap-southeast-2
    • ap-southeast-3
    • ap-southeast-4
    • ap-southeast-5
    • ap-southeast-6
    • ap-southeast-7
    • ca-central-1
    • ca-west-1
    • eu-central-1
    • eu-central-2
    • eu-north-1
    • eu-south-1
    • eu-south-2
    • eu-west-1
    • eu-west-2
    • eu-west-3
    • il-central-1
    • me-central-1
    • me-south-1
    • mx-central-1
    • sa-east-1
    • us-east-2
    • us-west-1
    • us-west-2
    Launch on AWS MarketplaceAWS launch steps

    5-day free trial, then from $0.04/hr software charge (larger instance sizes cost more) plus your own EC2 costs, billed by AWS.

    Subscriptions are open to AWS India (AISPL) accounts. Outside India? Ask us for a private build.

Getting started

From launch to signed in, step by step.

  1. Subscribe on AWS Marketplace and launch in your region with TCP 22, 80 and 443 open.

  2. Wait up to 15 minutes for first boot, then SSH in as ubuntu with your key pair and run sudo pc-credentials show to read this instance's random passwords (they are not the instance ID).

  3. Open https://<instance-public-ip>/, accept the one-time self-signed certificate warning and sign in as admin with the langflow password. Add your own model provider key in the model component; create API keys under Settings to call flows from your apps.

  4. Webmin is local only: run ssh -i key.pem -N -L 18000:127.0.0.1:8000 ubuntu@<instance-public-ip>, then open http://localhost:18000/ and sign in as admin with the webmin password.

  5. Change passwords with sudo bash /home/ubuntu/iscripts/pass_langflow.sh or pass_webmin.sh; check the server with sudo bash /home/ubuntu/iscripts/langflow_status.sh.

  6. Back up the application with sudo pc-backup create /var/backups/application.tar.gz and copy the file off the server.

Security posture

What this image does and does not ship with, one fact per line.

  • Clean-room build on Canonical's official Ubuntu 24.04 LTS image: Langflow is the official release, and nothing is copied from any third-party image.

  • No model weights or provider keys are included.

  • PostgreSQL listens only on the server itself, and the API needs a key or a signed-in user.

  • No password or key ships in the image: on first boot every instance creates its own random passwords, HTTPS certificate and server keys, which you read over SSH with `sudo pc-credentials show`.

  • Webmin listens only on the server itself and is reached through an SSH tunnel, SSH is key-only, and build-time SSH keys, host keys, machine ID, shell history and logs were removed before imaging.

  • Replace the self-signed certificate with a trusted one before production use, and restrict port 22 to trusted IP ranges in your security group.