Supermemory

MIT memory/context engine with a local API

AI Agents / Memory & Evals · OSS/MIT · 31.3k

Reviewed 2026-09-19 · last push 2026-10-18 · repo checked 2026-10-19

What's Good

MIT (supermemoryai/supermemory). Memory/context engine with an API and a documented local binary path, aimed at fast ingestion and retrieval for agent applications. The useful wedge is local/API speed and a practical developer surface rather than a research-only memory abstraction. The OSS tree is the free path when you run it locally.

The Catch

Vs Mem0 / Letta / Graphiti: Supermemory leans into a local/API speed angle, not the same graph-orchestration shape. pricing caveat: the pricing page gates self-hosted deployments to paid tiers while the README documents a free local binary — read “self-host” as the OSS/local path, not a promise that every production deployment tier is free. You still own data policy and retrieval quality.

Verdict

MIT memory/context engine. Fast local/API path; verify the paid self-host boundary before planning a hosted deployment.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/supermemory.svg)](https://stackgems.com/gems/supermemory)

HTML

<a href="https://stackgems.com/gems/supermemory"><img src="https://stackgems.com/badge/supermemory.svg" alt="Supermemory reviewed on Stack Gems" height="20"></a>

AI Agents →

Related