← Latest products

I compressed 10k PDFs into a 1.4GB video for LLM memory

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory. While building a Retrieval-Augmented Generation (RAG) system, I was frustrated by my vector database consuming 8GB RAM just to search my own PDFs.

Open source

17,328 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. A file-based agent memory framework that works like skill

    github.com

    Personal memory across agents

    Hacker News11 pts

  2. Continual Learning with .md

    github.com

    Turn your files into a memory filesystem for AI agents.

    Hacker News34 pts

  3. AI-Augmented Memory for Groups

    largemem.com

    We’re building Largemem, ( https://largemem.com ) a shared knowledge base where groups upload and maintain a common set of documents (PDFs, scans, audio) and query them conversationally.

    Hacker News10 pts

  4. A local-first memory store for LLM agents (SQLite)

    github.com

    Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

    Hacker News48 pts

  5. MemorySync

    memorysync.io

    Memory for AI Agents

    Hacker News22 pts