Supermemory

What is Supermemory?

Supermemory is a memory layer for AI agents and applications. Developers send it text, files, chats and web pages, and it builds user profiles and a memory graph that updates, merges and contradicts facts over time, then returns relevant context through a search call. It bundles five layers in one API: user profiles, the memory graph, hybrid retrieval, extractors for PDFs, images, audio and video, and connectors such as Notion, Google Drive, S3 and Gmail. Access is through a REST API, TypeScript and Python SDKs, plugins for tools like Claude Code and Cursor, and MCP. Pricing is usage based: every plan includes a monthly credit balance, and calls draw from it at the same published rates on all plans. Free is $0 with $5 of credits, Pro is $19/month, Max is $100/month, Scale is $399/month and Enterprise is custom. Qualifying startups and research teams can get Scale free for three months.

Use cases

• Give AI agents long-term memory
• Personalize chatbots with user profiles
• Search documents with managed RAG
• Sync Notion and Drive content into context
• Add memory to Claude Code or Cursor
• Build customer-support assistants that remember users

Who it's for

• AI developers
• Agent builders
• Startups
• Enterprise teams

Why use Supermemory

• One API covers profiles, memory, retrieval and connectors, so you avoid assembling a vector database stack.
• Pay only for what you use: rates are the same on every plan and plans just include a larger credit balance.
• Only new or changed content is billed when you update a document under the same id.
• Works with the agents and frameworks developers already use through plugins, MCP and SDKs.

Supermemory features

• User profiles built from behavior and context
• Memory graph that merges and updates facts
• Hybrid vector and keyword search
• SuperRAG multimodal extraction and chunking
• Connectors for Notion, Google Drive, S3 and Gmail
• TypeScript and Python SDKs plus REST API
• Plugins for Claude Code, Cursor and more
• Auto top-up with configurable limits
• SOC 2, HIPAA BAA and self-hosted option on Scale
• Usage-based rate card billed in SM tokens

Supermemory integrations

• Claude Code
• Cursor
• Windsurf
• Vercel AI SDK
• LangChain
• LangGraph
• CrewAI
• OpenAI SDK
• Mastra
• Zapier
• n8n
• Notion
• Google Drive
• Gmail
• S3

How to get started with Supermemory

1. Create an API key in the Developer Console and install the TypeScript or Python SDK, a plugin or the MCP server.
2. Add memories or documents with the add endpoint; Supermemory extracts, chunks and indexes the content.
3. Connect sources such as Notion, Google Drive or S3 so they sync automatically.
4. Search with a single call that combines semantic search and graph traversal, and pass the results to your model.
5. Watch usage against your monthly credit balance and set auto top-up if you need more.

Supermemory limitations

• Usage beyond included credits is billed at published rates
• Free plan includes 1 team seat and $5 of monthly credits
• Gmail connector starts at Max and S3 and web crawler at Scale
• Self-hosting and compliance options need Scale or Enterprise

Supermemory pricing

Yes, Supermemory has a free plan. Paid plans start at $19 per month, according to the official pricing page on 24 Oct 2026.

Supermemory plans

• Free

  $0

  per month

  • $5 of credits included every month
  • All plugins
  • Full search and memory API
  • 1 team seat, unlimited end users
  • Email support

• Pro

  $19/mo

  • $20 of credits included every month
  • Everything in Free
  • Auto top-up with purchase limits
  • 3 team seats
  • Priority support

• Max

  $100/mo

  • $130 of credits included every month
  • Everything in Pro
  • Gmail connector

• Scale

  $399/mo

  • $600 of credits included every month
  • Advanced PDF extraction
  • S3 and web crawler connectors
  • Unlimited team seats
  • SOC 2, HIPAA BAA, self-hosted option

• Enterprise

  Custom

  • Unlimited usage
  • Custom integrations and SSO
  • Forward-deployed engineer
  • Custom metering and billing

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

Supermemory alternatives

The main Supermemory alternatives listed on Debuly are Mem0, Zep, Letta, Cognee, LangMem and Pinecone. The table compares pricing and platforms; order is A–Z.

1. 

   Cognee

   Open-source memory engine for AI agents that combines vector search, knowledge graphs and relational storage, with a hosted cloud.

   Developer platformsAutomation and agentsResearch and search
   FreemiumVisit Cognee (official site)
2. 

   LangMem

   Python library from LangChain that gives AI agents long-term memory and lets them refine behavior from past conversations.

   Developer platformsAutomation and agents
   Open sourceVisit LangMem (official site)
3. 

   Letta

   Platform, formerly MemGPT, for building stateful AI agents with persistent memory, from a terminal app, SDK or API.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Letta (official site)
4. 

   Mem0

   Memory layer for AI agents and apps, available as an open-source package or a managed platform that keeps user context across sessions.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Mem0 (official site)
5. 

   Pinecone

   Managed vector database for AI search and RAG, with dense, sparse and full-text indexes, inference and an Assistant API.

   Developer platformsResearch and search
   FreemiumVisit Pinecone (official site)
6. 

   Zep

   Managed memory and context platform for AI agents, built on the Graphiti knowledge graph, with Python, TypeScript and Go SDKs.

   Developer platformsAutomation and agents
   FreemiumVisit Zep (official site)

Supermemory FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from supermemory.ai · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.