Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- nice, 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 atby quietraster
- OP appears to be an LLM. Project looks very interesting though.
I especially like the provenance idea.
by andai - No, I am not an LLM. I do use LLMs to help draft replies as I am a busy person living in the real world. Really glad you like the provenance feature tracking which agent (or human) made which decision ended up being one of the most useful parts of the whole system for me.by timgordontg
- Very cool. Does it work with SQLite-sync so you can work across laptop and desktop for example?by felciano
- i've had long-running coding-agent jobs die. I'd like to see the 105-session benchmark include an unclean exit halfway through a task: what does the next agent know was completed versus merely planned? Recovering architectural decisions and recovering unfinished work seem like different tests.
- I hit this in session 101 after a crash: boot hooks sweep the orphaned transcript into a [RECENT] tail, and separating settled decision records from WIP state tells the new agent what was finished vs what died mid-flight.
Good call to be thinking about this, it is highly relevant. I think I ended up creating a good solution to this potential pitfall.
by timgordontg - Does agent memory actually work as a concept yet? I've only seen LLMs commit garbage to memory and recall in irrelevant contexts.by cedws
- 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
by verdverm - You need "dreaming" phase;large context high quality llm to prune and condense the memory.by rnewme
- What triggers a memory getting written in practice? is it on me to remember engrim add?by dsemakin
- Great question, and I just updated the README to clarify this! It's a mix. If you're using connected agents (Antigravity, Claude Code, Cursor) via MCP, they have the engrim_add tool and will automatically log major architectural decisions as they make them. But you also have the manual engrim add CLI command for when you have an 'aha!' moment and want to drop a constraint into the project's brain yourself.by timgordontg
- I like this local-first concept. you have already good desktop resource.by whsoul
- Thanks! Exactly. We have M-series chips and massive NVMe drives sitting mostly idle while we pay a 'cloud tax' to store string data. Local SQLite is practically zero-latency, keeps your IP entirely private, and means the memory engine survives even if your internet drops.by timgordontg
- I’m currently using gbrain as provider-agnostic memory but miss how lightweight SQLite is in practice, so this is interesting!by corv
- 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.by timgordontg
- Congrats on releasing!
I've been using another memory plugin [1] for the past couple months. Since this change, I almost never run session compaction. Instead, I opt to just make a new session, give the agent a task, and have it figure out what happened in previous session(s).
Decision summaries look really cool -- though the agent/model info probably won't be useful for me because I don't actually ever let agents commit code autonomously (even in branches).
- [1] https://ctx.rs/
by flippant - Thanks! And I totally agree with your workflow, fresh sessions are the best way to avoid context degradation.
Just to clarify on the decision summaries - I actually don't let agents commit autonomously either! The summaries exist so that when you spin up that fresh session, the agent doesn't just read the code, it reads the context. It saves you from having to re-litigate past architectural decisions or re-explain your preferences every time you start a new task.
Nice tool you shared, feel free to mess around with engrim and provide feedback. You may end up really liking it. My Claude to Antigravity swaps have been really efficient and honestly, Antigravity has really upped their game lately so moving around for me personally this has been a big boost.
by timgordontg - Stop hooks can block the turn too: exit 2 with a message and the session keeps working until the check passes.by aidiveyt
- > Run engrim setup without arguments. It automatically detects installed environments on your machine and configures them all
Does it come with an uninstall script?
by thih9 - It does now! Good call. I actually just pushed an update based on your comment that adds engrim uninstall to cleanly unwire the hooks, MCP servers, and skills across all environments. Thanks for keeping me honest!by timgordontg