Perimattic Managed Langflow - AI Agent Builder on AWS

This AMI runs Langflow, the open-source visual builder for AI agents and retrieval-augmented generation (RAG) flows, with PostgreSQL 17 on Ubuntu 24.04 LTS. The container images are pinned to Langflow 1.13.0 (the official langflowai/langflow image) and PostgreSQL 17.11 and baked into the AMI, so first start does not depend on a registry. Langflow is an independent project and Perimattic is not affiliated with it.

Why Langflow?

Langflow lets you design agents, chains and RAG pipelines by connecting components on a canvas, test them in a built-in playground, and run them as an API or an MCP server. It works with the model providers and vector stores you choose.

What Perimattic adds

Secure by default: Langflow's automatic login, which would give any visitor a superuser session, is switched off. During first-login setup a random 24-character administrator password is generated on your server, the superuser is created from it, and public sign-up is closed. Setup then checks that a wrong password, the old default login and anonymous requests are refused, before the site is published. The secret key is generated per instance. No credential and no model provider key is included in the image: you add your own after you log in.

Pinned, tested versions: Langflow and PostgreSQL are fixed to exact tags, not 'latest', so a rebuild never changes the application behind your back.

HTTPS: Apache is configured as a reverse proxy and a free Let's Encrypt certificate is requested for your domain with certbot. Langflow listens only on the loopback interface and PostgreSQL only inside the Docker network. The interactive API documentation pages (/docs, /redoc, /openapi.json) are blocked in the Apache configuration. Usage data collection (DO_NOT_TRACK) is switched off.

Patched base: Ubuntu 24.04 LTS built through an automated EC2 Image Builder pipeline, with security updates applied at build time.

Limits

Langflow needs model provider API keys of your own (or a model you host) to do useful work, and outbound internet access to reach them. Langflow has no password-reset email or offline reset command in this configuration; change the generated password inside Langflow and keep it safe. Flows, users and variables are stored in PostgreSQL in /opt/app/postgres and files in /opt/app/data on the root volume: choose the EBS volume size for your use and take snapshots for backup. Memory use when idle was about about 1.2 to 1.5 GB for Langflow plus about 60 MB for PostgreSQL in our tests (a t3.small, 2 GB, ran but with little headroom); see the recommended instance type below.

Licence

Langflow is released under the MIT licence; this AMI runs the unmodified official image. PostgreSQL is released under the PostgreSQL License.

Getting Started Launch the AMI and open ports 22, 80 and 443 in the security group SSH in and answer the setup prompts (domain and admin email) Open https://your-domain  and sign in as admin with the password printed at the end of setup Add your model provider keys in Langflow (Settings > Global Variables) and build your first flow

A domain name with an A record pointing at the instance is required, because the site is served over HTTPS.

This AMI is built and supported by Perimattic.

Book a free setup consultation at https://cal.com/gaurav-pareek-perimattic/marketplace-setup-consultations  or email us at aws-support@perimattic.com .

Support Managed and supported by Perimattic, a cloud infrastructure company with 13+ years of experience serving global clients. We offer free setup assistance, custom integrations, infrastructure consulting, and 24/7 support.