DiffMem
AI
agent memory
SHOW HN2025
198points
45comments
#332of 3,837 in 2025
Top 9%of 2025 by points
How HN took it
CuriousMostly questions and neutral comments
6 positive, 13 neutral or asking, 1 mixed, 5 critical, out of 25 comments about the project. Thread score +0.08.
Idea: 4 for, 4 againstDocs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
Objections
Vector databases solve semantic search that BM25 keyword matching cannot
From 4 comments
I'm failing to grasp how it solves/replaces what vector db were created for in the first place (high-dimensional neighborhood searching, where the space to be searched grows by…
BenoitP on HNSomehow i feel like the op doesn't get what vector DB's are actually for, semantic search isn't the same as a markdown memory file
cchance on HNI mean these are two completely different approaches for completely different purposes. So saying that git replaces vector database is like saying that that a filing cabinet…
_pdp_ on HNThe submission and the readme fail to explain the important thing, which is how BM25 is run. If it creates bags of words for every document for every query, that would be…
OutOfHere on HN
Git is unnecessary complexity; a simpler store would do
From 1 comment
Maybe you can use Mercurial for this? You don’t need the complexity of Git for memory.
cc_ashby on HN
Requests
Evaluations comparing it against other memory approaches
From 1 comment
Seems really interesting! It would be great to see some evals to understand how well this works when stacked up against different approaches and use cases.
jmtulloss on HN
MCP server version
From 1 comment
This is cool! Do you have any plans on releasing it as an MCP server? Would love to add this to my mcp gateway service https://mcp-boss.com/ (shameless plug)
thecopy on HN
Questions
How BM25 index is built, updated and stored
From 1 comment
The submission and the readme fail to explain the important thing, which is how BM25 is run. If it creates bags of words for every document for every query, that would be…
OutOfHere on HN
How it compares to Graphiti/Zep temporal knowledge graphs
From 2 comments
Great idea! How does it compare to Graphiti / Zep? They use real time knowledge-graphs to tackle the problem you are trying to solve https://github.com/getzep/graphiti
albertdessaint on HNI could be wrong, but this seems to be exactly what Zep’s “Graphiti” library is made for, build as a semantic temporal knowledge graph.
fudged71 on HN
Alternatives named
Zep Graphiti temporal knowledge graph
From 3 comments
Great idea! How does it compare to Graphiti / Zep? They use real time knowledge-graphs to tackle the problem you are trying to solve https://github.com/getzep/graphiti
albertdessaint on HNI could be wrong, but this seems to be exactly what Zep’s “Graphiti” library is made for, build as a semantic temporal knowledge graph.
fudged71 on HNVery nice. We tackled the temporal issue "versioned" in your case with a temporal knowledge graph: https://www.falkordb.com/blog/building-temporal-knowledge-graphs-graphiti/
danshalev7 on HN
Standard RAG with vector embeddings
From 2 comments
> I have struggled to get any of the RAG approaches to handle this effectively. You need to annotate your text chunks. For example you can use a LLM to look over the chunks and…
visarga on HNSuper simplistic example, but say i mention my Daughter, who is 9. Then mention she is 10, a few years later she is 12 but now i call her by her name. I have struggled to get any…
alexmrv on HN