Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)

by zaydmulani • 2 months ago

60 31 2 months ago

Given the abundance of vaguely similar local-first AI memory layers, it might be a good idea to add a "Why Mnemo" section right at the top of README.md to explain why folks should consider using it.

cush2• 2 months ago

Or just wait a week and whatever’s built into your harness de jour will be as good or better than whatever homebrew solutions are out there

Most LLMs forget everything the moment a conversation ends. mnemo fixes that

Even the opening line of the README is obviously very out of date. Might be true if you’re raw-dogging a model or using a basic agent SDK

SwellJoe3• 2 months ago

After working with LLMs a bunch, I now want them to forget everything every time I end the conversation. Otherwise they get dumber and more confused over time.

LLMs do not have memory and these "memory" systems that everyone makes don't change that fact. They just clutter up context with probably irrelevant noise. I don't want the LLM to remember everything I've ever said and try to make every project align with often contradictory or unrelated facts, rules, guidelines, practices, whatever, because when it tries it gets messier and makes worse software.

I don't want the LLM to be my friend and remember my birthday. I have it write plans, developer docs, test suites, and static analysis into every project. That's the "memory". It's compatible with every agent, it's in their native tongue (Markdown and code), and it's focused on the specific project.

zaydmulani9• 2 months ago

Done "Why mnemo" section added to the README with a comparison table. Short version: single Rust binary, zero cloud, petgraph knowledge graph with multi-hop traversal, scored retrieval. Link in case you want to check it: github.com/zaydmulani09/mnemo

bilbo-b-baggins• 2 months ago

You forgot BM25 embeddings.

https://github.com/MikeS071/ai-engram

https://github.com/lamost423/openclaw-hybrid-memory

https://medium.com/@qdrddr/agentic-memory-framework-hindsigh...

https://clawhub.ai/vnesin-sarai/hybrid-retrieval

https://www.josecasanova.com/blog/openclaw-qmd-memory

https://medium.com/@richardhightower/stop-the-hallucinations...

https://github.com/oomkapwn/enquire-mcp#-why-its-the-best

https://github.com/rohitg00/agentmemory#key-capabilities

https://github.com/Melody-0321/NE-Memory-Core

https://github.com/ClaudioDrews/memory-os

https://en.wikipedia.org/wiki/Okapi_BM25

It is based on the probabilistic retrieval framework developed in the 1970s and 1980s

Anyway, good for ya, hope you had fun building it.

asdev• 2 months ago

I haven't seen one unique product in AI, everyone is building the same thing

andai• 2 months ago

Do any of them work properly yet?

zaydmulani9• 2 months ago

Fair. The differentiator is the Rust single binary + petgraph knowledge graph. No Python runtime, no cloud, survives restarts. Built it because nothing local fit that profile.

zaydmulani9• 2 months ago

BM25 is in my other project vecdb. mnemo's retrieval is graph-first — entity deduplication, multi-hop traversal, session-scoped scoring. Different tradeoff, not an oversight.

SwellJoe3• 2 months ago

Everybody builds one. And, then they usually figure out that making the model fill its context with a bunch of memories hurts performance more often than it helps.

esafak• 2 months ago

That's why I always ask: got benchmarks?

zaydmulani9• 2 months ago

Yes — cargo run -p mnemo-bench. Ships with 12 benchmarks. Full retrieval pipeline is ~4ms on debug build. Numbers are in the README performance table.

phantomathkg• 2 months ago

Is there any relevance with another tool call mnemon?

zaydmulani9• 2 months ago

Different project — mnemon is a Python-based memory tool. mnemo is a Rust binary with a knowledge graph layer and REST API sidecar. Similar name, different approach.

ksajadi• 2 months ago

I tend to agree with the rest of the commenters that the most likely outcome is that harnesses will include features like this. I had a slightly different issue and that was 'project-level memory' that i can use across models or harnesses (chat, claude code, etc).

for a while i used Obsidian but it was not very good with hosted tools like claude.ai then i moved to a combination of Linear and Notion. Still using Linear but Notion ended up being a royal pain: it is built for humans not agents. It is block based and when multiple agents use it there is a lot of corruption in the process.

I wanted a markdown only, notion built for agents that can work with multiple agents so built one: markbase.cloud

feel free to try and use it. i think it's useful

fjwood694• 2 months ago

Yes, the multi-agent governance takes a lot of solving.. thus far I've gotten Hermes writing to the same memory store that Claude code, antigravity, cursor, etc can all contribute, pull from, but it's taken a whole separate layer of governance.

Agents that can write to shared memory are powerful. Agents that can write to shared memory without oversight are a liability. Mori has the governance layer - https://github.com/fjwood69/mori

pylotlight• 2 months ago

Brew installation? Not looking to use pip or load manually.

For single bins or otherwise, brew is definitely preferred.

zaydmulani9• 2 months ago

Homebrew tap is on the roadmap. For now the fastest path on Mac is cargo install --path crates/mnemo-api or the Docker one liner. Will add a brew tap for v0.2.0.

vichoiglesias• 2 months ago

I think we are all experiencing more or less the same kind of pain regarding memory+llms, and love to see how different approaches exist this problem.

How does mnemo decides when to forget something? So old history wont pollute the new answers?

zaydmulani9• 2 months ago

Currently mnemo doesn't have automatic forgetting it's on the v0.2.0 roadmap. The mitigation right now is that retrieval scoring weights recency, so older chunks naturally rank lower than recent ones. A TTL system and explicit memory decay are the right long-term fix. Good callout.

andywidjaja• 2 months ago

Nice approach, the Rust performance and single-binary deployment are compelling. Question, how do you handle contradictory facts? If John moves from Stripe to Google, does the graph resolve that, or does it store both?

zamalek• 2 months ago

and injects relevant context back into future prompts

It looks like this is left as an exercise for the student?

Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)

Related Stories