Rekal
AI
llm memory
SHOW HN2026
9points
10comments
#3,371of 4,366 in 2026
Top 78%of 2026 by points
How HN took it
MixedNo clear lean
3 positive, 2 neutral or asking, 0 mixed, 1 critical, out of 6 comments about the project. Thread score 0.00.
Execution: 1 for, 1 againstDesign: 2 for, 0 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
What people liked
Hybrid search scoring is well thought out
From 1 comment
The hybrid search scoring is really well thought out. One question: are the 0.4/0.4/0.2 weights fixed or configurable? To me it feels like different use cases would want…
eitanlebras on HN
Clean project
From 1 comment
Nice clean project - Python 3.14 as a requirement might be an issue for adoption...
axeldunkel on HN
Objections
Python 3.14 requirement may hinder adoption
From 1 comment
Nice clean project - Python 3.14 as a requirement might be an issue for adoption...
axeldunkel on HN
Requests
Make hybrid search weights (0.4/0.4/0.2) configurable
From 3 comments
The hybrid search scoring is really well thought out. One question: are the 0.4/0.4/0.2 weights fixed or configurable? To me it feels like different use cases would want…
eitanlebras on HNAll memories should not decay at the same rate. these weights should be configurable !
SachitRafa on HNI think that'd be cool, maybe just a simple config option in pyproject.toml or a .rekal/config.yml would cover most use cases: they could default to 0.4/0.4/0.2 but could be…
eitanlebras on HN
Questions
How effective has it been for the maker's own use, and where does it fall over?
From 1 comment
I’m going to try this out. Curious how effective it’s been for your own use, OP? Anything particularly interesting or where it still falls over and requires tuning that you’ve…
alsetmusic on HN