← Latest products

SOTA long memory eval with open source models

We built a multi-stage retrieval system that scores among the best on LongMemEval, using only open-source models. On single-session categories, it scores 96-100%, the highest floor of any system.

Visit ensue.devexternal site

Reactions (1)

Similar products

by description similarity

  1. 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

  2. Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload

    github.com

    OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

    Hacker News22 pts

  3. A tool to give large language models better memory

    github.com

    A memory framework for Large Language Models and Agents.

    Hacker News11 pts

  4. Honcho

    github.com

    Open-source memory infrastructure, powered by custom models

    Hacker News8 pts

  5. Explore large language models with 512MB of RAM

    github.com

    Explore large language models in 512MB of RAM

    Hacker News138 pts