Illustration of what supermemory does: Memory layer that lets AI assistants and apps remember users across conversations

supermemoryai /

supermemory

Memory layer that lets AI assistants and apps remember users across conversations

  • 31.4k stars
  • 296 stars since 3 Oct
  • TypeScript
  • Updated today
  • Some experience
  • Memory, RAG & data
Open on GitHub (opens in a new tab) Website (opens in a new tab)

AI assistants forget everything between conversations. Supermemory sits beside them and keeps a memory. It pulls facts out of what users say, tracks changes and contradictions, and drops information that has expired.

You can use it in three ways. Plugins and an MCP server add memory to tools like Claude Code, Cursor and Codex. A TypeScript and Python SDK lets developers add memory to their own apps. A local server runs the same API on your machine.

It handles the vector database, embedding and chunking steps for you. It combines document search (RAG) and personal memory in one query, and keeps a profile of stable facts and recent activity for each user. The README says it ranks first on three memory benchmarks. That is the team's own claim, so check the research page yourself.

What it does

  • Automatic memory extraction

    Pulls facts out of conversations, handles updates and contradictions, and forgets expired information.

  • User profiles

    Keeps long-term facts and recent context for each user. One call returns the profile, and the README says it takes about 50ms.

  • Hybrid search

    One query searches both your documents and the user's memories. A search mode setting lets you search memories only.

  • Connectors and file processing

    Syncs Google Drive, Gmail, Notion, OneDrive and GitHub. It also processes PDFs, images, videos and code.

  • Local and offline mode

    A single binary serves the same API at localhost:6767. With Ollama and local embeddings, nothing leaves your machine.

What you could build

  • Give Claude Code or Cursor persistent memory of your preferences and projects through a plugin or the MCP server.
  • Add per-user memory and profiles to a chatbot or agent built with the Vercel AI SDK, LangChain or Mastra.
  • Search company documents from Google Drive or Notion together with each user's personal context.
  • Run a private memory server offline with Ollama for prototyping or sensitive data.
  • Compare memory providers on standard benchmarks using the MemoryBench framework.

Get started

For the SDK, install the package, create a client, then add content and ask for a profile. To run it yourself, install the local binary and start supermemory-server, which prints an API key. Then point the client's baseURL at http://localhost:6767.

npm install supermemory
pip install supermemory
curl -fsSL https://supermemory.ai/install | bash

Commands are copied from the project's README. Read it on GitHub for the full setup.

More in Memory, RAG & data

See all
firecrawl Web API that turns sites and search results into markdown or JSON for LLMs 194.3k6.7k markitdown Python tool that turns PDFs, Office files, audio and more into Markdown for LLMs 191.7k3.8k graphify Maps a codebase and its docs into a knowledge graph your AI assistant can query 133.1k9.9k claude-mem Saves what your coding agent does and feeds the useful parts back into later sessions 102.3k7.2k vectorize-io/hindsight Memory server that lets AI agents store, search and learn from past interactions 52.8k8.1k OpenViking A context database that stores agent memory, docs and skills as browsable files 40.6k1.5k open-notebook Self-hosted research notebook that chats with your documents using any AI provider 40.5k776 WeKnora Self-hosted platform that turns documents into RAG search, an agent and a wiki 35.1k3.4k gbrain A shared memory for AI agents that stores sourced facts and answers with citations 31.1k593 qmd Local command-line search for your notes, docs and transcripts, with AI re-ranking 30.6k421

    ↑↓ to move, Enter to open, Esc to close