← Latest products

Yet another memory system for LLMs

Persistent memory for LLMs and apps. Content-addressed storage with dedupe, compression, full-text and vector search. Built this for my LLM workflows - needed searchable, persistent memory that wouldn't blow up storage costs.

Open source

373 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

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

    Hacker News48 pts

  2. Turn your files into a memory filesystem for AI agents.

    Hacker News34 pts

  3. 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.

    Hacker News61 pts

  4. Personal memory across agents

    Hacker News11 pts

  5. Wordllama

    github.com

    Things you can do with the token embeddings of an LLM

    Hacker News370 pts