snap-stanford/memorilla
🦍 Memorilla: Latent Semantic Memory for LLMs
- Stars770
- LanguagePython
- LicenseApache-2.0
🦍 Memorilla: Latent Semantic Memory for LLMs
🦍 Memorilla: Latent Semantic Memory for LLMs
This repository provides code for training and evaluating Memorilla, a memory system that gathers information from an entire document collection into a fixed number of query-dependent memory tokens for a frozen LLM. The code is based on our paper Memorilla: Latent Semantic Memory for LLMs.
A frozen LLM can only use what fits in its context window, so Memorilla reads an entire document collection, such as a user's past chats or a long book, and hands the LLM just 16 memory tokens that carry what each question needs. With this small budget, it achieves the best average performance against methods such as Mem0 and MemoRAG, and on FactKG it is even more accurate than giving the LLM every document (84.33%…
Description and README excerpt from snap-stanford/memorilla on GitHub ↗.
snap-stanford/memorilla was first seen on GitHub · Trending Python today on Nov 10, 2026. Since then it has appeared in 2 checks on 1 different day. Its best position was #15 of 16, reached on Nov 10, 05:25 UTC. It dropped off the list after Nov 10, 08:25 UTC.
Position on GitHub · Trending Python today at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by GitHub.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 10, 08:25 UTC, after 1 day of trending.
#15 on GitHub · Trending Python today, on Nov 10, 05:25 UTC. Trendoday checks this list every 180 minutes.
It was first seen on Nov 10, 2026 and has been on the list on 1 day (2 checks) since.
Mostly Python; it is licensed under Apache-2.0. It has 770 stars and 60 forks.