Updated

Supermemory

Memory and continual-learning API for agents that extracts what it learns about each user or tenant into a vector-graph store and injects it into the model's context, available as an API, plugins and an MCP server.

4 open-source projects declare Supermemory in their code; 2 makers' products we track use it.

Open sourceFree tierPaid from $19/mo

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Supermemory

Makers' products we track use Supermemory for agent memory (2).

What Supermemory is used for

Agent Memory · Hosted memory API →A memory API that learns from users' chats, files and URLs and injects what it knows into the model's context, also available as plugins and an MCP server.Trade-off: Credit-based billing makes heavy ingestion harder to predict; self-hosting is only on the Scale plan and above.
Letta3Mem02Supermemory2Graphiti1Zep0Makers' products on each, for agent memory

When to use Supermemory, and when not

Pick Supermemory if

  • You want to add user memory to an existing agent with a few API calls and a free tier to start. Agent Memory →

Something else fits better if

  • Memory must stay on your own infrastructure, built as a graph over your data: Cognee or Graphiti.
  • Your agent needs dated facts that change over time, from business data as well as chats: Zep or Graphiti.
  • You'd rather build the agent on a platform where memory is built in: Letta.
  • You want memory as plain Markdown files you can read, edit and share across your own AI tools: Basic Memory.
From each decision's guide, written from what makers' products chose and why.

How Supermemory itself is built

27 tools, from its own code, website and Product Hunt page.

Who uses it

2 makers' products, each linked to the source that shows it, and 4 open-source projects that declare it in their code. The best known on Product Hunt: Shadow (1,169 followers), Clade (635 followers).

The maker says so 2Declared in code 4How evidence is collected →
Clade
CladeAI COO that runs your team in tools you already use

“OpenAI's memory lives in one chat session. Clade needed a shared brain across agents, channels, and clients - Supermemory gave us one memory layer the whole stack reads and writes to.”

Agent MemoryMaker says so · source ↗
Shadow
ShadowReal-time AI for smarter calls and faster follow-ups

“The cleanest way to connect memory to your applications. Supermemory just works, quietly, in the background.”

Agent MemoryMaker says so · source ↗

Open source: a project that declares Supermemory as a dependency in its public code — verifiable, but not necessarily a live product.

Alternatives to Supermemory

All alternatives by situation →

Questions makers ask about Supermemory

What is Supermemory used for?

Memory and continual-learning API for agents that extracts what it learns about each user or tenant into a vector-graph store and injects it into the model's context, available as an API, plugins and an MCP server. Makers' products we track use it for agent memory (2).

When should you use Supermemory?

You want to add user memory to an existing agent with a few API calls and a free tier to start (agent memory). Something else fits better if: Memory must stay on your own infrastructure, built as a graph over your data, pick Cognee or Graphiti; your agent needs dated facts that change over time, from business data as well as chats, pick Zep or Graphiti.

Is Supermemory free?

Yes — there is a free tier a small product can run on; paid use starts at $19/mo. source ↗

Is Supermemory open source or self-hostable?

Open source. source ↗

Can AI coding agents work with Supermemory?

No llms.txt, official MCP server or CLI found yet.

Who uses Supermemory?

2 makers' products we track, each with a source, and 4 open-source projects declare it in their code. The best known of them on Product Hunt: Shadow (1,169 followers), Clade (635 followers). source ↗