Supermemory review

Q: How do I install Supermemory?

Run npm install supermemory. It needs Node.js >=18. The install section above has the other options from the project's README.

Supermemory is a memory and context engine for AI apps and agents, available as an API, plugins, an MCP server, and a self-hosted binary.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

Supermemory is a memory and context layer that extracts facts from conversations, builds user profiles, and combines RAG with memory search. It is for developers adding memory to agents and for users of AI coding tools like Claude Code and Cursor. It can run on the hosted API or fully locally with the same API.

31.5kGitHub stars
+120new stars, week of Oct 25
~209.2kdownloads a week, +11% vs 4-week avg
#21in RAG, data and memory this week

Supermemory at a glance

Category: RAG, data and memory
Maintained by: supermemory (organization, @supermemoryai on GitHub)
License: MIT
Language: TypeScript, MDX, Python
Repository: github.com/supermemoryai/supermemory
Website: supermemory.ai/docs
npm package: supermemory 5.0.2
PyPI package: supermemory 5.0.0
Latest release: supermemory 5.0.2 on npm, Oct 13, 2026
First published: Feb 27, 2024

What Supermemory does

Supermemory extracts facts from conversations and handles temporal changes, contradictions, and automatic forgetting of expired information.
Supermemory maintains user profiles with stable facts and recent activity, returned in one call.
Supermemory runs hybrid search that combines knowledge base documents and personalized memories in a single query.
Supermemory auto-syncs Google Drive, Gmail, Notion, OneDrive, GitHub, and a web crawler through connectors with real-time webhooks.
Supermemory processes PDFs, images with OCR, videos with transcription, and code with AST-aware chunking.
Supermemory gives AI coding tools persistent memory through plugins and an MCP server with memory, recall, and context tools.
Supermemory offers wrappers for Vercel AI SDK, LangChain, LangGraph, OpenAI Agents SDK, Mastra, Agno, Claude Memory Tool, and n8n.

How it works

Supermemory is used through TypeScript or Python SDKs, a hosted MCP server, or plugins for coding tools. Memory is scoped by container tags. The local server runs on http://localhost:6767 with an embedded graph engine and local embeddings by default. It connects to OpenAI, Anthropic, Gemini, Groq, OpenAI-compatible endpoints, or Ollama. Moving from local to hosted only requires changing baseURL.

How to install and start using Supermemory

SDK with npm

npm install supermemory

SDK with pip

pip install supermemory

Local server

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

Requirements

Node.js 18 or later for the TypeScript library.
Python 3.10 or later for the Python library.
An API key; the local server requires it even on localhost.
An LLM provider key or Ollama for self-hosting; Docker images support Linux amd64 and arm64.

First steps

Store content for a user with client.add(), passing the content and a containerTag such as user_123.
Call client.profile() with the containerTag and a query to get the user profile and relevant memories.
For coding tools, add https://mcp.supermemory.ai/mcp as the supermemory server in your MCP client config.
For local use, run supermemory-server, complete the first-boot wizard, and use the printed API key.

Who Supermemory is for

Developers adding memory, RAG, and user profiles to AI agents through one API.
Users of Claude Code, Cursor, Codex, or OpenCode who want memory across conversations.
Teams that want to prototype memory locally or offline before shipping on a hosted platform.

Limitations to know

The self-hosted lite version is licensed up to 10,000 documents, and the cap is enforced at the API.
Offline mode covers text memories; URL ingestion uses a hosted reader service.
API v3 and v4 are deprecated and will shut down on December 31, 2026.
Running docker compose down -v deletes the data volume and keys.

Is Supermemory growing? Usage data

In the week of Oct 25–31, 2026, Supermemory ranked #203 on the Devtoolwatch Board and #21 in RAG, data and memory, with a momentum score of 44 out of 100. Its main package had about 209.2k downloads that week, +11% against its own 4-week average.

New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).

Show the weekly numbers

New GitHub stars per week for Supermemory
Week of	New stars
Aug 9, 2026	120
Aug 16, 2026	104
Aug 23, 2026	147
Aug 30, 2026	112
Sep 6, 2026	422
Sep 13, 2026	1k
Sep 20, 2026	300
Sep 27, 2026	166
Oct 4, 2026	135
Oct 11, 2026	107
Oct 18, 2026	132
Oct 25, 2026	120

On Hacker News

Best Open-Source Embedding Models Benchmarked and Ranked, 6 points and 0 comments (Jun 27, 2025)
Supermemory: AI second brain for all your saved stuff, 5 points and 3 comments (Jul 22, 2024)
Show HN: We added memory to Claude Code. It's powerful now, 5 points and 0 comments (Jan 30, 2026)

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

Supermemory alternatives

Other RAG, data and memory tools on the Board in the week of Oct 25–31, 2026, by momentum:

RAG, data and memory ranked by momentum, the week of Oct 25–31, 2026
Rank	Tool	Stars	Downloads/wk
#1	XERJXERJ is a local-first search engine and MCP server for AI agents, packaged as one Rust binary with an Elasticsearch-compatible API.	17.9k	–
#2	MemvidMemvid is a single-file memory layer for AI agents that packages data, embeddings, search indexes, and metadata into one portable .mv2 file.	17.3k	–
#3	LEANNLEANN is a Python vector database and RAG library that recomputes embeddings on demand to keep indexes small on personal devices.	13.7k	–
#4	GraphifyGraphify is an AI coding assistant skill that turns a codebase, with its docs, PDFs, images and videos, into a queryable knowledge graph.	140k	480.7k
#5	MarkItDownMarkItDown is a lightweight Python utility from Microsoft that converts PDFs, Office documents, images, audio and other files to…	193.2k	4.7M
#6	FirecrawlFirecrawl is an API and open source project to search, scrape, crawl, and interact with web pages, returning LLM-ready markdown or JSON…	197.4k	2.9M

All RAG, data and memory tools, ranked

Recent Supermemory releases

server-v0.0.9, Oct 12, 2026
server-v0.0.9-rc.3 (pre-release), Oct 12, 2026
server-v0.0.8, Aug 17, 2026
server-v0.0.7, Aug 15, 2026
server-v0.0.7-rc.2 (pre-release), Jul 22, 2026

Supermemory FAQ

Is Supermemory free and open source?

Yes. Supermemory's source code is on GitHub (supermemoryai/supermemory) under the MIT license, so you can use it for free.

How do I install Supermemory?

Run npm install supermemory. It needs Node.js >=18. The install section above has the other options from the project's README.

Is Supermemory still maintained?

Yes. The supermemoryai/supermemory repository was last updated on Oct 21, 2026, and the latest release, supermemory 5.0.2 on npm, came out on Oct 13, 2026.

How popular is Supermemory?

Supermemory has 31.5k GitHub stars as of Nov 1, 2026. It gained 120 new stars in the week of Oct 25–31, 2026, against a 12-week average of 240 a week. Its main package had about 209.2k downloads that week, +11% against its own 4-week average. That made it #21 among RAG, data and memory tools on the Devtoolwatch Board.

Supermemory vs Mem0: how do they compare?

Supermemory and Mem0 are both tracked by Devtoolwatch as RAG, data and memory tools. Supermemory has 31.5k GitHub stars and Mem0 has 68.2k. In the week of Oct 25–31, 2026, Supermemory's main package had 209.2k downloads and Mem0's had 884.1k. Mem0 is a memory layer for AI agents and apps that stores and retrieves user, session, and agent context across interactions. Mem0 review.

Supermemory vs Honcho: how do they compare?

Supermemory and Honcho are both tracked by Devtoolwatch. Supermemory has 31.5k GitHub stars and Honcho has 7.9k. Honcho review.

What are the best alternatives to Supermemory?

Other RAG, data and memory tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: XERJ (#1), Memvid (#2), LEANN (#3), Graphify (#4), MarkItDown (#5). The alternatives table above has their numbers.

What is Supermemory?

Supermemory is a memory and context layer for AI. It learns from conversations, extracts facts, builds user profiles, handles updates and contradictions, and returns relevant context. It also includes RAG, connectors, and file processing.

How does Supermemory work?

Supermemory extracts important facts from conversations and stores them, scoped by container tags. A memory engine tracks updates and forgets expired info, user profiles hold static and dynamic facts, and hybrid search returns documents and memories together.

How is Supermemory different from RAG?

Supermemory treats memory and RAG as separate. RAG retrieves document chunks and gives everyone the same results. Memory tracks facts about users over time, such as a new city replacing an old one. Supermemory runs both together by default.

Does Supermemory work with VS Code?

Supermemory lists VS Code as a supported MCP client, along with Claude Desktop, Cursor, Windsurf, Claude Code, OpenCode, OpenClaw, and Hermes. You add the MCP server URL to the client config.

Can Supermemory run fully locally?

Supermemory can run locally as one binary or with Docker. It uses local embeddings by default and can point at Ollama for offline text memories. Data lives in ~/.supermemory. URL ingestion still uses a hosted reader service.

Sources

Supermemory README badge

Maintainers can show the tool's weekly Board rank in their README:

[![Devtoolwatch](https://index.devtoolwatch.com/badge/supermemory.svg)](https://index.devtoolwatch.com/tools/supermemory/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].