← Latest products

Long term Memory and 50M token window for LLM

Join the discussion on this paper page.

Visit huggingface.coexternal site

Reactions (1)

Similar products

by description similarity

  1. Tokensift

    github.com

    an open-sourced token-efficiency linter for LLM prompts

    Hacker News6 pts

  2. LLM Token Visualizer

    v0-llm-token-visualizer.vercel.app

    How big is 128k token input

    Hacker News6 pts

  3. 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

  4. Fixing LLM memory degradation in long coding sessions

    github.com

    Empirical proof of SOTA LLM (GPT-5/Gemini-Pro/Claude-Pro) context saturation in complex engineering. Contains the "Misuraca Protocol" for deterministic logical segmentation to prevent entropy drift.

    Hacker News5 pts

  5. Speeding up LLM inference 2x times (possibly)

    asciinema.org

    Here's a project I've been working on for the last few months.

    Hacker News419 pts