Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agent memory as a file format

calpaterson.com

Post reply on HN
Print view View original

101–110 of 115 posts

Re: Agent memory as a file format

#101

Post by calpaterson »

kelseyfrog wrote: post #76

> A memoryfield page looks like this: --- title: Carbon Fibre Woks created: '2026-03-01T09:00:00Z' updated: '2026-08-22T14:30:00Z' uuid: 6aa615f0-486f-48a7-a210-ba4f5ff18c8b summary: Thermal properties of carbon fibre cookware --- Carbon fibre woks conduct heat evenly, but... So basically recfiles[1], and an entire suite of tools replaced by fopen and sed. Anyone who doesn't know of recfiles is doomed to reimplement…

Thanks for pointing out recfiles. I was not aware of it and will investigate whether we can reuse anything. That said Markdown with YAML frontmatter is not exactly my own invention!

Re: Agent memory as a file format

#102

Post by calpaterson »

mofosyne wrote: post #98

Instead of having to regenerate a zip file everytime you add/delete a memory... could we just use a git repo of markdown pages? This buys you incremental writes, commit hash pinning and diffs for free. In addition to having a git archive outputting a zip export as well? Main wrinkle is you would need to gitignore the sqlite database as it doesn't store very well in git (binary, changes lots per insert). But it's easy…

You don't have to regenerate a zipfile each time you do something - the zipfile is just to give a single file for distribution. It's just a zip of the directory.

Git is supported in the spec, though the tool doesn't yet handle it (soon! git is nice as you get a log "for free" which helps agents understand more about the memories).

As for sqlite in git: yes you can gitignore it, you could use git-lfs, you could use an out of band database. It would be great if there were another format more amenable to git to store vectors in. I looked at csv closely, but I was worried about float formatting/representational bugs. There is a gap in the market for a format here.

Re: Agent memory as a file format

#103

Post by calpaterson »

jing09928 wrote: post #97

Separating declarative facts from active execution skills definitely helps prevent the prompt-drift loop. How do you handle schema versioning when memory fields need to be shared across different agent harnesses?

I'm not sure I understand - the schema is set and doesn't get changed by agents as they work

Re: Agent memory as a file format

#107

Post by r14c »

It isn't done enough to share yet, but I've been having fun experimenting with a knowledge graph backed by sqlite, using the tool call schema from mcp-server-memory.

My main gripe so far is that I have to push the agent to maintain an organized graph. Once its there, it can be pretty useful to keep track of small notes which would otherwise be sprinkles all over my projects. The kg has some design limits that make poisoning hard to diagnose, so that's still on the list to fix.

Re: Agent memory as a file format

#108

Post by manganate06 »

threecheese wrote: post #79
dataviz1000 wrote: post #25

Does anyone else not use memory? I find once there is one poisoned line of text it negatively affects everything else downstream. Instead, I use a temp/ folder with documents and use different files for different agents and models. Then I have to constantly prune and delete the files. Any information that can be extrapolated is just noise which negatively affects the agent. If you have a definition of a database stru…

I have memory disabled in all my Chat UIs (even though it tends to creep in, looking at you ChatGPT). It’s very helpful until it scales with time, at which point it becomes useless due to staleness or mis-application across contexts. That being said, in coding over a longer time horizon, having the agent continually re-derive decisions/laws/facts/etc from your code is wasteful of tokens and time, and if your code doe…

[flagged]

Re: Agent memory as a file format

#110

Post by hectdev »

mistermann wrote: post #42
hectdev wrote: post #39

Earlier quoted context omitted.

I have mine self record into Supabase for my projects and a local sqlite for work. It determines a method of record keeping which I audit every week to hone the process. Really makes it so I can move to any provider I want and I have a queryable memory store. Also really helps when someone asks about why some feature was implemented a certain way. I also have it learn from corrections in PRs and comments made overtim…

> It determines a method of record keeping which I audit every week to hone the process I would like to hear more details of what it ended up with for a structure

[flagged]
Post reply on HN