Loading page
Loading page

Developer tools
A self-hosted sync server and dashboard that shares your AI coding agent's memory across machines and teammates.
Engram gives AI coding agents memory that lasts past one session. Normally an agent forgets your project when the chat ends. With Engram, the agent saves and searches notes through MCP, a CLI or an HTTP API. Locally it is a single Go binary with a SQLite database and full-text search.
This template runs Engram Cloud, the optional server part. It replicates memory per project between machines and gives you a web dashboard. It uses PostgreSQL for storage. Your local SQLite file stays the main copy, and sync only happens for projects you enroll.
It is for developers who use agents such as Claude Code, Codex, Cursor or Gemini CLI on more than one machine. It also suits small teams who want agents on a shared project to work from the same memory.
Agent memory holds details about your code, your architecture and sometimes your clients. A self-hosted sync server keeps that in your own database, under your own token, rather than on someone else's service.
The trade-off is that you run a server for a tool that also works offline. You keep the token secret, update the image when the CLI moves forward, and back up the PostgreSQL data. The docs note the CLI and server versions should match.
Containers: postgres:16-alpine, ghcr.io/gentleman-programming/engram:1.16.3
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Engram, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Engram setup screen.