supermemory  by supermemoryai

Second brain for LLMs, providing contextual knowledge

created 1 year ago
10,218 stars

Top 5.0% on sourcepulse

GitHubView on GitHub
Project Summary

Supermemory provides a scalable, self-hostable memory API designed to augment Large Language Models (LLMs) with contextual knowledge. It targets developers and individuals seeking to build AI-powered applications or enhance personal knowledge management by transforming scattered data into actionable insights. The core benefit is enabling LLMs with relevant, easily searchable personal or organizational data.

How It Works

Supermemory acts as a universal engine for LLM memory, focusing on data organization and search. It ingests data from various sources (web pages, bookmarks, contacts, tweets, Notion) and stores it in a searchable format, leveraging Postgres with Pgvector for efficient similarity search. The architecture comprises a web UI (Remix, Hono), a Chrome extension for easy data capture, and a backend powered by Cloudflare Workers, utilizing R2 for object storage and Cloudflare KV for caching. This stack prioritizes speed, scalability, and self-hostability.

Quick Start & Requirements

  • Install/Run: Self-hosting instructions are available in SELF-HOSTING-GUIDE.md. A Chrome extension is available on the Chrome Web Store.
  • Prerequisites: Postgres with Pgvector, Cloudflare Workers, R2 Object storage, Cloudflare KV.
  • Setup: Detailed self-hosting guide provided.

Highlighted Details

  • Features include ideation capture, bookmark management, contact storage, Twitter bookmark import, powerful search, chat with collections, and memory refresh for re-learning.
  • Offers a Supermemory API for developers to build custom applications.
  • Integrates with Telegram, Twitter, Chrome bookmarks, and Notion.
  • Privacy-focused and self-hostable.

Maintenance & Community

  • Developed by a college student.
  • Supported by sponsors including Cloudflare, Vercel, and Coderabbit.
  • Contributions are welcome.

Licensing & Compatibility

  • Licensed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License (CC BY-NC-SA 4.0).
  • Permits personal projects with attribution. Requires open-source for non-commercial use. Commercial use requires direct contact for licensing.

Limitations & Caveats

The CC BY-NC-SA 4.0 license restricts commercial use without explicit permission, potentially limiting adoption in enterprise environments. The project is primarily developed by a single individual, which may impact long-term maintenance and development velocity.

Health Check
Last commit

2 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
3
Star History
893 stars in the last 90 days

Explore Similar Projects

Starred by Andrej Karpathy Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), Alex Cheema Alex Cheema(Cofounder of EXO Labs), and
3 more.

Perplexica by ItzCrazyKns

0.3%
23k
AI-powered search engine alternative
created 1 year ago
updated 1 day ago
Feedback? Help us improve.