News for hackers. Stuff that matters.

A comment on Show HN: Rekal – Long-term memory for LLMs in a single SQLite file.

Re:Show HN: Rekal – Long-term memory for LLMs in a single SQ... by eitanlebras on Monday April 13, 2026 @02:54PM (#47756377)
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 different balances (e.g. a coding assistant would want higher recency weights than a research tool would).
[ Parent | on HN ]
Re:Show HN: Rekal – Long-term memory for LLMs in a single SQ... by jeeybee on Monday April 13, 2026 @05:10PM (#47757862)
The 0.4/0.4/0.2 weights are just based of hand wavy trail an error, will look into other options. I could make them configurable?
[ Parent | on HN ]
Re:Show HN: Rekal – Long-term memory for LLMs in a single SQ... by eitanlebras on Monday April 13, 2026 @05:48PM (#47758266)
I 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 overriden.
[ Parent | on HN ]
Re:Show HN: Rekal – Long-term memory for LLMs in a single SQ... by jeeybee on Tuesday April 14, 2026 @02:13AM (#47761872)
Added a mcp command for it, but i might add it as a comfig as well?

https://github.com/janbjorge/rekal/pull/14/changes

[ Parent | on HN ]
Re:Show HN: Rekal – Long-term memory for LLMs in a single SQ... by eitanlebras on Tuesday April 14, 2026 @11:08PM (#47774241)
Nice! Yeah, maybe adding it as a quick config could be very helpful to embed it into Rekal's structure.
[ Parent | on HN ]