[bilbo-b-baggins]

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]

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

[zaydmulani]

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.

[fractorial]

I rolled the same thing in Go months ago as I am sure at least another 1000 people have in their own way.

[zaydmulani]

Would genuinely be interested to see it. link? The graph traversal approach seems underexplored compared to pure vector search.

[andai]

Do any of them work properly yet?

[fjwood69]

sure they do.. but it's painful

how to capture, what to capture, when to capture it.. where to put it.. how to make it 'useful'.. how to reinject it or make it accessible

the harness makers may well come up with better means than flat files, but there are loads of folks out there working across different harnesses and in teams, and there's very little that works in that respect.

why I built mori - https://github.com/fjwood69/mori

use it solo, use it in your homelab/office, use it in the cloud with a team..

[zaydmulani]

Checked out mori — the governance layer for multi-agent writes is exactly the gap mnemo doesn't address yet. Good work on that.

[fjwood69]

Got a bit carried away with the governance aspect.. and after lots of testing, I've published a whitepaper which I think you will find interesting.

Link is in my profile.

[fjwood69]

Cheers — quite a bit more work going into that presently and extensive testing to back it up. Early finding: auto-extracted memory is no better than a hand-written doc. Human curation is the lever. Numbers at the top of the mori README.

[zaydmulani]

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.