supermemory
SHA-256State-of-the-art memory and context engine for AI agents and apps. #1 on major AI memory benchmarks. One API for persistent memory, RAG, user profiles, and connectors.
Smart Download
Download Download Version
vserver-v0.0.3 · 229.6 MB
The #1 AI memory engine on benchmarks. Gives persistent memory to AI agents and apps via a single API or MCP. Supports self-hosting.
Core Features
- Automatic fact extraction from conversations, handles temporal changes, contradictions, and forgetting
- Auto-maintained user profiles (static facts + recent activity) in ~50ms per call
- Hybrid search: RAG + Memory combined in one query
- Built-in connectors: Google Drive, Gmail, Notion, OneDrive, GitHub with real-time sync
- Multi-modal extractors: PDF, OCR, video transcription, code with AST-aware chunking
What It Can't Do
- •Cloud API requires registration for an API key (free quota limited). Local mode may need network access to model inference endpoints for remote LLMs. MCP clients must support OAuth or manual API key configuration. Multi-modal extraction relies on external models (OCR, transcription) which may not work fully offline.
Use Cases
- AI personal assistant: install browser extension or MCP client to give Claude/Cursor persistent memory of your preferences and projects
- AI product development: add memory, RAG, user profiles, and connectors to agents via a single API, no vector DB setup needed
Detailed Introduction
Supermemory is an open-source memory and context layer for AI that solves the problem of AI forgetting between conversations. It automatically extracts facts, builds user profiles, handles temporal changes and contradictions, and delivers the right context at the right time. Top-ranked on LongMemEval, LoCoMo, and ConvoMem benchmarks. Unlike Mem0 which focuses on simple memory retrieval, Supermemory offers a full context stack including hybrid search (RAG + Memory), multi-modal extractors (PDF, OCR, video transcription), and auto-syncing connectors (Google Drive, Notion, GitHub). It can run fully locally with a single binary or be used via cloud API. Supports multiple AI frameworks (Vercel AI SDK, LangChain, Mastra) and MCP protocol. The project includes a consumer app, browser extension, and plugins for Claude Code, Cursor, and more.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Download and install the Supermemory local runtime: curl -fsSL https://supermemory.ai/install | bash (or grab the binary from Releases)
Install the SDK via npm install supermemory or pip install supermemory, then call client.add() to store memories
For AI clients (Claude Desktop, Cursor, etc.), configure the MCP server URL https://mcp.supermemory.ai/mcp to enable memory
- Download and install the Supermemory local runtime: curl -fsSL https://supermemory.ai/install | bash (or grab the binary from Releases)
- Install the SDK via npm install supermemory or pip install supermemory, then call client.add() to store memories
- For AI clients (Claude Desktop, Cursor, etc.), configure the MCP server URL https://mcp.supermemory.ai/mcp to enable memory
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
4036486514bd3511099e8f8642e1c56ecc58550c5e194442e88a5438992c0957This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
If using the local binary, delete the downloaded executable and remove the ~/.supermemory data directory. If installed via npm/pip, run npm uninstall supermemory or pip uninstall supermemory.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
AnythingLLM
Chat with your docs, use AI agents, multi-user support, runs locally with zero setup.
goose
Goose is a general-purpose AI agent that runs on your machine. Use it for coding, research, writing, automation, and more. It offers a native desktop app (macOS, Linux, Windows), a full CLI, and an API. Works with 15+ providers (Anthropic, OpenAI, Google, Ollama, etc.) and connects to 70+ extensions via the Model Context Protocol. Built in Rust, part of the Linux Foundation.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.