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

Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

github.com

Post reply on HN
Print view View original

81–90 of 140 posts

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#81

Post by Myrmornis »

zby wrote: post #62

Reviewed: https://zby.github.io/commonplace/agent-memory-systems/revie... It is a third llm wiki on front page in 24 hours! Obviously it is a hot topic. I have my own horse in that race - so I might not be objective - but I've compiled a wishlist for these system: https://zby.github.io/commonplace/notes/designing-agent-memo... I wish there was a chance for collaboration - everybody coding their own system seems like…

Your notes look really interesting, thanks. I'm curious --from the prose style it's clear they were written by an LLM. For design notes like this do you sort of have a mental TODO to go back and write them up in your own words to make sure they really capture your own opinions?

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#82

Post by najmuzzaman »

zby wrote: post #62

Reviewed: https://zby.github.io/commonplace/agent-memory-systems/revie... It is a third llm wiki on front page in 24 hours! Obviously it is a hot topic. I have my own horse in that race - so I might not be objective - but I've compiled a wishlist for these system: https://zby.github.io/commonplace/notes/designing-agent-memo... I wish there was a chance for collaboration - everybody coding their own system seems like…

love the "Borrowable Ideas" section. would suggest to definitely borrow them.

full disclosure: we started as a context infra company (nex.ai) from long long before Karpathy even came up with the LLM wiki idea, and have barely exposed any of that stuff to WUPHF but starting to open some of that now. glad to see the concerns in the comparison are things that our context infra already built for.

still, happy to collab & share learnings, and of course avoid duplication.

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#83

Post by zby »

Myrmornis wrote: post #81
zby wrote: post #62

Reviewed: https://zby.github.io/commonplace/agent-memory-systems/revie... It is a third llm wiki on front page in 24 hours! Obviously it is a hot topic. I have my own horse in that race - so I might not be objective - but I've compiled a wishlist for these system: https://zby.github.io/commonplace/notes/designing-agent-memo... I wish there was a chance for collaboration - everybody coding their own system seems like…

Your notes look really interesting, thanks. I'm curious --from the prose style it's clear they were written by an LLM. For design notes like this do you sort of have a mental TODO to go back and write them up in your own words to make sure they really capture your own opinions?

For the design notes like: https://zby.github.io/commonplace/notes/designing-agent-memo... - I iterate over and over to clean them. This one is also a compilation with many intermediate documents.

But the reviews are written automatically - here are the instructions: https://github.com/zby/commonplace/blob/main/kb/agent-memory...

Overall the knowledgebase is a mixture of these. I have this disclaimer on the first page:

This KB is itself agent-operated: a human directs the inquiry, AI agents draft, connect, and maintain the notes. The framework for building knowledge bases is documented using that framework.

I hope it is enough - I've seen many people get angry with publishing LLM generated work.

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#84

Post by najmuzzaman »

dataviz1000 wrote: post #25

LLM models and the agents that use them are probabilistic, not deterministic. They accomplish something a percentage of the time, never every time. That means the longer an agent runs on a task, the more likely it will fail the task. Running agents like this will always fail and burn a ton of token cash in the process. One thing that LLM agents are good at is writing their own instructions. The trick is to limit the…

[dead]

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#85

Post by kaoD »

dhruv3006 wrote: post #2

I love that so many people are building with markdown ! But also would like to understand how markdown helps in durability - if I understand correctly markdown has a edge over other formats for LLMs. Also I too am building something similar on markdown which versions with git but for a completely different use case : https://voiden.md/

I'm interested. At a glance this sounds a lot like Hurl[0]. What's the difference?

[0] https://hurl.dev/

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#86

Post by psanchez »

dominotw wrote: post #56
psanchez wrote: post #45

Earlier quoted context omitted.

Even though I did not know about Andrej Karpathy's tweet from earlier this month, I ended up converging on something very similar. A couple of weeks ago I built a git-based knowledge base designed to run agents prompts on top of it. I connected our company's ticketing system, wiki, GitHub, jenkins, etc, and spent several hours effectively "onboarding" the AI (I used Claude Opus 4.6). I explained where to find company…

how is this related to parent comment . slop.

Well, my comment was meant as an example of a setup for actually building something real with reasonable quality. I was answering to that part of the previous comment.

In my experience, the difference is context. Agents without structure produce slop, but with a well-curated knowledge base and iteration, they can be useful. I was just sharing a setup that has been working for me lately.

Edit: minimal changes for clarity

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#87

Post by mohamedkoubaa »

danielbln wrote: post #57
mohamedkoubaa wrote: post #51

Earlier quoted context omitted.

In my over a decade of experience as a software engineer, writing code was always a smaller fraction of my time compared to reading code, debating code with colleagues, and wrangling ops. Optimizing for velocity of writing code will inevity lead to spaghetti at best and vaporware at worst.

There is also discussion, ping pong with the agent, exploring parallel paths, quickly experimenting, analyzing code, researching things. A code agent can do more than "write me as much code as possible, go!".

That's how I use agents, but I see less experienced engineers brag about how much code they pump out and it makes me cringe

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#88

Post by Bridged7756 »

_zoltan_ wrote: post #29
portly wrote: post #20

I don't understand the point of automating note taking. It never worked for me to copy paste text into my notes and now you can 100x that? The whole point of taking notes for me is to read a source critically, fit it in my mental model, and then document that. Then sometimes I look it up for the details. But for me the shaping of the mental model is what counts

Then you have never worked at a large enough codebase or across enough many projects?

It all boils down to the same thing. Work out a system that makes you function. It's as simple as a PKMS of your liking, the problem is that people are allergic to writing their thoughts down.

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#89

Post by Bridged7756 »

portly wrote: post #20

I don't understand the point of automating note taking. It never worked for me to copy paste text into my notes and now you can 100x that? The whole point of taking notes for me is to read a source critically, fit it in my mental model, and then document that. Then sometimes I look it up for the details. But for me the shaping of the mental model is what counts

Ditto.

It circles back to the question, is this unimportant enough for me to delegate it to a LLM that might get it wrong? If the answer is yes, why even do it to begin with. If the answer is no, you have to do it manually.

I personally though, see value in this type of automation. Stuff like tag categorization, indexing, that otherwise would've been lost seems like a good fit for LLMs. Whether or not they're an ideal solution and something else like a search engine would've been a better fit, is a different question.

Post reply on HN