Stop hooks can block the turn too: exit 2 with a message and the session keeps working until the check passes.
Updated in v1.3.1
Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
81–87 of 87 posts
Re: Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
#82Very cool. Does it work with SQLite-sync so you can work across laptop and desktop for example?
just pulled in engrim merge - check v1.3.1
Re: Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
#83nice, zero cloud lock-in for agent memory is exactly what i want. how do you handle conflicts when two agents write to the same sqlite store at
just pulled in engrim merge - check v1.3.1 (sorry for duplicate reply - had another that was basically same topic) Trying to reply to everyone - thank you.
Re: Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
#84To all the people who didn’t flag the article but seem intent on flagging all Tim’s responses to questions, please stop. You’re making it quite annoying for those of us that want to see those responses.
Seriously, thank you so much.
Re: Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
#85Earlier quoted context omitted.
gbrain is an awesome project, but yeah, that was exactly the itch I was trying to scratch! I wanted something that felt as fast, portable, and bulletproof as a single .db file. Zero background daemons or cloud dependencies—just fast, hybrid queries.
thanks for sharing, I can appreciate those qualities
You are super welcome
Re: Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
#86Earlier quoted context omitted.
Permanent docs definitely belong in git. This is just the desk scratchpad for messy session context so you can /clear freely without cluttering commit history or burning tool calls on grep. Anti Gravity has a large enough context window that seems to be less needed than Claude Code but the real value now with engrim is if you are using multiple services, your project is relevant when switching services. This was born…
Ahh, interesting. I have an issue today where my GitHub agentic workflows keep blowing through the context window that my local models can support; it ends up spending most of its runtime compacting over and over again. I've done all the usual stuff to slim down the fixed context and prevent it from slurping up too many files but it's still a recurring issue. Now I'm wondering if I can put engrim in the gh-aw contain…
Sure thing. If you find something related to an edge case, let me know specifically and I can try to work it into future improvements.
Re: Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
#87Does agent memory actually work as a concept yet? I've only seen LLMs commit garbage to memory and recall in irrelevant contexts.
don't let them decide on memories like you shouldn't really be having them write skills or agents.md files I use them to produce candidates, but not make the decision, there's almost always something wrong in there and in need of an editorial pass. They tend to be overly verbose too, keep em short and sweet
[dead]