trvon

yams

C++2025–2025

trvon / yams

yams

Persistent memory for LLMs and apps. Content-addressed storage with dedupe, compression, full-text and vector search.

AI & Machine Learning Data & Databases Productivity Search & Information Retrieval

Explore on GitHub Read Hacker News discussions

3Distinct people

4Mentions

0Explicit recommenders

372GitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

Persistent memory for LLMs and apps. Content-addressed storage with dedupe, compression, full-text and vector search.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour4 dated mentions

Observed mentions: 2025-08-14 03:34:11 UTC to 2025-08-14 14:21:34 UTC.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Submissions	Comments
Aug 14, 03:00	2025-08-14 03:00:00 UTC	2025-08-14 04:00:00 UTC	1	1	0
Aug 14, 04:00	2025-08-14 04:00:00 UTC	2025-08-14 05:00:00 UTC	0	0	0
Aug 14, 05:00	2025-08-14 05:00:00 UTC	2025-08-14 06:00:00 UTC	0	0	0
Aug 14, 06:00	2025-08-14 06:00:00 UTC	2025-08-14 07:00:00 UTC	0	0	0
Aug 14, 07:00	2025-08-14 07:00:00 UTC	2025-08-14 08:00:00 UTC	0	0	0
Aug 14, 08:00	2025-08-14 08:00:00 UTC	2025-08-14 09:00:00 UTC	0	0	0
Aug 14, 09:00	2025-08-14 09:00:00 UTC	2025-08-14 10:00:00 UTC	1	0	1
Aug 14, 10:00	2025-08-14 10:00:00 UTC	2025-08-14 11:00:00 UTC	1	0	1
Aug 14, 11:00	2025-08-14 11:00:00 UTC	2025-08-14 12:00:00 UTC	0	0	0
Aug 14, 12:00	2025-08-14 12:00:00 UTC	2025-08-14 13:00:00 UTC	0	0	0
Aug 14, 13:00	2025-08-14 13:00:00 UTC	2025-08-14 14:00:00 UTC	0	0	0
Aug 14, 14:00	2025-08-14 14:00:00 UTC	2025-08-14 15:00:00 UTC	1	0	1

What Hacker News says

4 sources

blackmanta·Aug 14, 2025

The system is honestly tuned for storage efficiency not speed but these configurations are tunable and you can use the benchmarks as a reference for tuning. https://github.com/trvon/yams/blob/main/docs/benchmarks/perf...

In Show HN: Yet another memory system for LLMs

sync·Aug 14, 2025

It, uh... generates mock embeddings? https://github.com/trvon/yams/blob/c89798d6d2de89caacdbe50d2... (seems like there's some vague future plans for models like all-MiniLM-L6-v2, all-mpnet-base-v2)

In Show HN: Yet another memory system for LLMs

paffdragon·Aug 14, 2025

You mean these? https://github.com/trvon/yams/tree/main/include/yams

In Show HN: Yet another memory system for LLMs

blackmanta·Aug 14, 2025Submission

Show HN: Yet another memory system for LLMs

Built this for my LLM workflows - needed searchable, persistent memory that wouldn't blow up storage costs. I also wanted to use it locally for my research. It's a content-addressed storage system with block-level deduplication (saves 30-40% on typical codebases). I have integrated the CLI tool into most of my workflows in Zed, Claude Code, and Cursor, and I provide the prompt I'm currently using in the repo. The project is in C++ and the build system is rough around the edges but is tested on macOS and Ubuntu 24.04.

165 points · Open discussion