---
title: "What is Supermemory?"
description: "Supermemory is the long term and short term context and memory infrastructure for agents."
sidebarTitle: "What is Supermemory?"
icon: "/icons/hugeicons/book-open-01.svg"
---
export const ArtTile = ({ title, href, children }) => {
return (
)
}
export const At = ({ x, y, w, className, children }) => (
{children}
)
export const Tile = ({ x, y, size = 36, logo, on, badge, children }) => (
{children}
{badge ? : null}
)
export const Lines = ({ d }) => (
)
Supermemory is **context infrastructure for AI agents**. It gives your agent memory, retrieval and user profiles through one API, and you can configure each part for your use case.
These are the building blocks it ships with:
Prefers PythonUses TypeScriptUpdatesBun for scripts
refund policy for annual plans0.92
profile.md
notes.md
meetings
Maya KapoorPayments engineer
Based in BerlinStatic
Fixing webhooksDynamic
PDF
LongMemEval
Supermemory1st
With Supermemory, your agent remembers what each user has told it and uses that to answer more personally and more consistently.
Supermemory leads the LongMemEval and LoCoMo benchmarks and independent ones such as SWEContext. See the [benchmark results](https://supermemory.ai/research).
## How does it work? (at a glance)

- You send Supermemory raw data in any format - text, files, and chats, or connect it to the data sources
- Supermemory [intelligently indexes them](/concepts/how-it-works) using our user understanding model and builds a semantic understanding graph on top of an entity (e.g., a user, a document, a project, an organization). We call these entities a `namespace` (v3/v4 called it a container tag)
- This knowledge is now traversed by the agent, and an automatic profile is built for it. The agent may now use it for memory operations or for retrieval.
## Why add memory to your agent?
Without memory, every session starts from zero. The model cannot know what the user preferred last week, which project they are on, or that a fact has changed since yesterday.
Memory gives an agent a lasting understanding of people and entities over time: their preferences, decisions, relationships and corrections. Retrieval (RAG) grounds answers in documents and knowledge bases. Most agents need both.
With memory, your agent can:
- Personalize answers with preferences, roles and history from earlier sessions, without putting the whole chat log in every prompt.
- Stay correct when facts change. If a user says "I love Adidas" and later "I'm switching to Puma", only the newer preference should hold.
- Pull the right policy, ticket or document when a question needs source material.
- Keep each customer's memory separate, so one user's data never leaks into another's.
Think of memory as the context a good teammate carries in their head, not a search box over raw logs. To see where retrieval ends and memory begins, read [Memory vs RAG](/concepts/memory-vs-rag).
## Why Supermemory?
- **State of the art on long-horizon memory** — #1 on [LongMemEval](https://supermemory.ai/research), [LoCoMo](https://supermemory.ai/research), and [ConvoMem](https://supermemory.ai/research), plus independent benches like [SWEContext](https://arxiv.org/pdf/2602.08316)
- **Memory is a graph, not a blob store** — facts [update, connect, and forget](/concepts/graph-memory) in real time; not nearest-neighbor chunks alone
- **User profiles built in** — static + dynamic context the agent should [always know](/concepts/user-profiles), ~ready for the prompt
- **Memory + SuperRAG in one engine** — personalize *and* ground on the same `namespace` / context pool
- **Every door, one store** — API, [MCP](/supermemory-mcp/mcp), plugins, [SMFS](/smfs/overview), and connectors share the same memories
- **Multimodal by default** — text, chats, PDFs, images, video, code via [extractors](/concepts/content-types) and [connectors](/connectors/overview)
- **Run it your way** — managed cloud or [self-host](/self-hosting/overview) as a single binary (including offline)

Memory, profiles, and SuperRAG share the **same context pool** when you use the same isolation (`namespace`). Mix and match for your product! A namespace can be anything - a user, a project, team, organization, etc.
## Next steps
Make your first API call in minutes
Understand the knowledge graph architecture
vs DIY vectors, thin memory layers, pure RAG
One binary, zero config, fully offline
Credits, SM tokens, and how usage works
SOC 2, GDPR, HIPAA BAA, encryption