Hitchhikethe internet
Directory/Memory systems/Supermemory
Memory systems · Tool

Supermemory

Researched

Context infrastructure for AI agents providing persistent, structured memory built as a knowledge graph with sub-300ms hybrid search. Works with any model, handles diverse data types, and offers connectors, plugins, and enterprise compliance.

Online Checked
Official websiteVisit website
Official site snapshots

See the official site at a glance

Read-only public captures of Supermemory’s homepage. Screenshots are dated, never live embeds, and open full-screen.

Visit live site
Homepage · captured Jul 21, 2026
1 earlier capture
At a glance

In one minute

Start here for the decision-making essentials: what Supermemory does, who it is for, how it is accessed, and the first-party sources behind this profile.

Pricing5 options

Free tier available to start building

Usage-based pricing with $5 of free monthly usage

paid tiers: Pro $19/mo, Max $100/mo, Sc

Free to get started (Hermes agent integration)

The Claude Code, Cursor, and OpenCode plugins are free and no longer require a paid plan

Platforms
Web
API accessNot public
FoundedNot disclosed by source
AvailabilityWeb / remote
LicenseProprietary

Best suited to

Source-backed fit
Teams building AI agents that need persistent user memory Developers replacing fragile RAG stacks with a unified memory API Companies wanting fast agent-context integration Organizations needing SOC 2 and HIPAA-compliant agent memory
Decision support

Common questions and adoption checks

5 sourced answers

Short answers to the questions buyers and builders commonly ask about Supermemory. Each answer cites the shared ledger below, where every source is listed once.

01What does Supermemory help with?

Persistent, structured memory built as a knowledge graph using a custom user understanding · Hybrid search, reranking, and structured context for documents at sub-300ms latency (Super · Extractors that turn PDFs, web pages, images, audio, and raw files into agent-ready memory · One memory API that replaces fragile RAG stacks and stitched-together vector databases

Supermemory
Ledger citation[1] supermemory.ai
02Who is Supermemory intended for?

Teams building AI agents that need persistent user memory · Developers replacing fragile RAG stacks with a unified memory API · Companies wanting fast agent-context integration (days, not quarters) · Organizations needing SOC 2 and HIPAA-compliant agent memory

Customers have integrated Supermemory in a single day
Ledger citation[3] supermemory.ai/case-studies
03What pricing information is available for Supermemory?

Free tier available to start building · Usage-based pricing with $5 of free monthly usage; paid tiers: Pro $19/mo, Max $100/mo, Sc · Free to get started (Hermes agent integration) · The Claude Code, Cursor, and OpenCode plugins are free and

Free tier available to start building
Ledger citation[3] supermemory.ai/case-studies
04Does Supermemory document API access?

No public API access is listed in the recorded profile sources.

One memory API that replaces fragile RAG stacks and stitched-together vector databases
Ledger citation[3] supermemory.ai/case-studies
05What integrations does Supermemory document?

Connectors for Slack, Notion, Drive, Gmail, GitHub, S3, and custom sources with automatic · Customers have integrated Supermemory in a single day · API, OpenClaw, Hermes agent, AI SDK, Mastra (with @supermemory/tools v2.0.0) · Supermemory provides plugins for Claude Code, Cursor, and OpenCode. · Google Drive

Connectors for Slack, Notion, Drive, Gmail, GitHub, S3, and custom sources with automatic syncing
Ledger citation[1] supermemory.ai
Decision guide

Capabilities and operating fit

Memory systems

This profile connects the jobs Supermemory is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.

Common use cases

  • Long-term and short-term memory for AI agents
  • Storing, extracting, retrieving, and operating on agent context
  • Providing perfect recall about users for personalized AI agents
  • Building semantic understanding graphs over users, documents, and projects
  • Powering agents through SMFS (Supermemory Filesystem)
  • Context infrastructure for AI agents

Access signals

Pricing model
Free tier available to start building · Usage-based pricing with $5 of free monthly usage; paid tiers: Pro $19/mo, Max $100/mo, Sc · Free to get started (Hermes agent integration) · The Claude Code, Cursor, and OpenCode plugins are free and no longer require a paid plan;
API
Not publicly listed
Source links
7 recorded
Source-backed

Verified facts

Updated July 20, 2026

Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.

Official website

HTTP 200 verified twice

[1]supermemory.ai
First-party description

Supermemory

[1]supermemory.ai
Source-supported facts

Persistent, structured memory built as a knowledge graph with custom graph engine · Hybrid search, reranking, and structured context at sub-300ms latency · Works with any model

[1]supermemory.ai
Capability

Persistent, structured memory built as a knowledge graph using a custom user understanding model, powered by dynamic dreaming and a custom graph engine

[1]supermemory.ai
Capability

Hybrid search, reranking, and structured context for documents at sub-300ms latency (SuperRAG)

[1]supermemory.ai
Platform

Native POSIX filesystem on macOS and Linux (uses ls, cat, and grep)

[1]supermemory.ai
Integration

Connectors for Slack, Notion, Drive, Gmail, GitHub, S3, and custom sources with automatic syncing

[1]supermemory.ai
Capability

Extractors that turn PDFs, web pages, images, audio, and raw files into agent-ready memory objects with smart chunking

[1]supermemory.ai
View 32 more verified facts
Model

Works with any model

[1]supermemory.ai
Capability

One memory API that replaces fragile RAG stacks and stitched-together vector databases

[3]supermemory.ai/case-studies
Platform

Product lineup includes Connectors, MCP Plugins, RAG, Memory Graph, Personal App, and Developer Console

[3]supermemory.ai/case-studies
Api

Developer Console provides API keys, usage data, and documentation

[3]supermemory.ai/case-studies
Pricing

Free tier available to start building

[3]supermemory.ai/case-studies
Use case

Context infrastructure for AI agents

[3]supermemory.ai/case-studies
Integration

Customers have integrated Supermemory in a single day

[3]supermemory.ai/case-studies
Pricing

Usage-based pricing with $5 of free monthly usage; paid tiers: Pro $19/mo, Max $100/mo, Scale $399/mo; Enterprise custom

[6]supermemory.ai/pricing
Use case

Context infrastructure for AI agents — storing, extracting, retrieving, and operating on agent context

[6]supermemory.ai/pricing
Platform

Products include Connectors, MCP, Plugins, RAG, Memory Graph, and a Personal App

[6]supermemory.ai/pricing
Capability

Per-user memory graph with auto-built profiles and fact hierarchies that let agents learn in real time

[6]supermemory.ai/pricing
Api

Supermemory API token pricing: $0.005 per 1K SM tokens; Rich content at $0.010 (described as 2× cheaper)

[6]supermemory.ai/pricing
Security

Scale tier includes SOC 2 and HIPAA BAA compliance with a self-hosted option; Enterprise offers air-gapped self-hosting, dedicated managed instances, SOC 2, HIPAA, GDPR, custom contracts, DPA, uptime SLA, and a priority Slack channel

[6]supermemory.ai/pricing
Capability

Long-term and short-term memory and context infrastructure for AI agents

[2]supermemory.ai/docs/intro
Capability

State of the art across LongMemEval and LoCoMo benchmarks

[2]supermemory.ai/docs/intro
Use case

Providing perfect recall about users to build AI agents that are more intelligent, personalized, and consistent

[2]supermemory.ai/docs/intro
Capability

Ingests text, conversations, files (PDF, Images, Docs), and videos

[2]supermemory.ai/docs/intro
Capability

Builds a semantic understanding graph on top of entities such as users, documents, projects, or organizations

[2]supermemory.ai/docs/intro
Capability

Bundled context stack including agent memory, content extraction, connectors and syncing, and a managed RAG platform

[2]supermemory.ai/docs/intro
Capability

Memory layer for AI agents

[4]supermemory.ai/blog
Capability

SMFS (Supermemory Filesystem) - filesystem redesigned for agents with special files, structures, and commands

[4]supermemory.ai/blog
Use case

Used by hundreds of companies to power their agents

[4]supermemory.ai/blog
Capability

Dynamic Dreaming - automatically connects the dots

[4]supermemory.ai/blog
Integration

API, OpenClaw, Hermes agent, AI SDK, Mastra (with @supermemory/tools v2.0.0)

[4]supermemory.ai/blog
Pricing

Free to get started (Hermes agent integration)

[4]supermemory.ai/blog
Platform

Supermemory offers products including Connectors, MCP, Plugins, RAG, Memory Graph, and Personal App.

[5]supermemory.ai/changelog
Integration

Supermemory provides plugins for Claude Code, Cursor, and OpenCode.

[5]supermemory.ai/changelog
Pricing

The Claude Code, Cursor, and OpenCode plugins are free and no longer require a paid plan; free-tier accounts can use them.

[5]supermemory.ai/changelog
Api

Scoped API keys that can add memories can now call the v4 conversations endpoint (POST /v4/conversations) with the same container-tag and write-access protections as memory ingestion.

[5]supermemory.ai/changelog
Deployment

Supermemory offers a self-hosted server that turns documents into memories and supports search.

[5]supermemory.ai/changelog
Capability

The TypeScript SDK allows calling client.search() once with a searchMode parameter to return memories, documents, or both.

[5]supermemory.ai/changelog
Capability

Handles extraction for text, conversations, files (PDF, Images, Docs), and videos

[2]supermemory.ai/docs/intro
Practical capabilities

What it helps with

8 documented areas

A concise view of the jobs, capabilities and integrations described in the recorded product sources.

Use case

Long-term and short-term memory for AI agents

Use case

Storing, extracting, retrieving, and operating on agent context

Use case

Providing perfect recall about users for personalized AI agents

Use case

Building semantic understanding graphs over users, documents, and projects

Use case

Powering agents through SMFS (Supermemory Filesystem)

Use case

Context infrastructure for AI agents

Use case

Providing perfect recall about users to build AI agents that are more intelligent, persona

Use case

Used by hundreds of companies to power their agents

Availability

Where it runs and where to get it

Source checked

Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.

Cost / license

Free tier available to start building · Usage-based pricing with $5 of free monthly usage; paid tiers: Pro $19/mo, Max $100/mo, Sc · Free to get started (Hermes agent integration) · The Claude Code, Cursor, and OpenCode plugins are free and no longer require a paid plan;

Platforms

Native POSIX filesystem on macOS and Linux (uses ls, cat, and grep)Product lineup includes Connectors, MCP Plugins, RAG, Memory Graph, Personal App, and DeveProducts include Connectors, MCP, Plugins, RAG, Memory Graph, and a Personal AppSupermemory offers products including Connectors, MCP, Plugins, RAG, Memory Graph, and Per
Implementation details

Adoption notes

DeploymentSupermemory offers a self-hosted server that turns documents into memories and supports se · Cloud services
LicenseNot disclosed by source
Model supportWorks with any model
Data controlScale tier includes SOC 2 and HIPAA BAA compliance with a self-hosted option; Enterprise o
Learning curveIntermediate
Primary use casesLong-term and short-term memory for AI agents, Storing, extracting, retrieving, and operating on agent context, Providing perfect recall about users for personalized AI agents, Building semantic understanding graphs over users, documents, and projects, Powering agents through SMFS (Supermemory Filesystem), Context infrastructure for AI agents, Context infrastructure for AI agents — storing, extracting, retrieving, and operating on a, Providing perfect recall about users to build AI agents that are more intelligent, persona, Used by hundreds of companies to power their agents

What to verify before adopting

    Evolution and major updates

    Supermemory timeline

    A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.

    Research in progress
    Scheduled for research

    Building a reliable release history.

    This profile is being checked for dated releases and material product changes. Nothing appears here until the exact date and event can be verified from a recorded source.

    Dated event Short explanation Original source
    Citation ledger

    Recorded sources

    7 unique pages

    Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.

    1. 1supermemory.ai 9 facts · 2 answers · Official site
    2. 2supermemory.ai/docs/intro 10 facts · Documentation
    3. 3supermemory.ai/case-studies 6 facts · 3 answers · Official site
    4. 4supermemory.ai/blog 6 facts · Official site
    5. 5supermemory.ai/changelog 6 facts · Official site
    6. 6supermemory.ai/pricing 6 facts · Pricing
    7. 7supermemory.ai/privacy 6 facts · Security
    Research status48 substantive facts · 7 source pages · quality score 91/100