Live data from Hacker News

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

github.com

101–110 of 140 posts

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

#101
post #18

Cool idea. But is anyone actually building real stuff like this with any kind of high quality? Every time I hear someone say "I have a team of agents", what I hear is "I'm shipping heaps of AI slop".

I remember the personal wiki was a bit of trend 5 years ago but it kind of died because it had an unclear purpose for the most part. I kept one but never really referred to any of the notes and then just went back to a paper and to do list. I’m sure this is useful for those who kept up the habit.

this is not a personal wiki though. it is a team wiki. agents are responsible to manage it and keep it fresh and always visible with human oversight.

tbh this won't be much useful as a personal wiki.

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

#102
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…

[dead]

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

#103
post #17

Any particular reason for BM25? Why not just a table of contents or index structure (json, md, whatever) that is updated automatically and fed in context at query time? I know bag of words is great for speed but even at 1000s of documents, the index can be quite cheap and will maximise precision

[dead]

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

#104

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/

[dead]

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

#105

Would be great if the provider layer supported arbitrary OpenAI-compatible endpoints — DeepSeek, for example. Any plans?

supported via OpenCode, which is the runtime that speaks the OpenAI-compatible surface. DeepSeek exposes that surface, so the path is: point OpenCode at the DeepSeek base URL and key, then set OpenCode as your synthesis or runtime CLI in the WUPHF config.

can also do llama.cpp server, LM Studio, LocalAI, OpenRouter, Together, Anyscale, and anything else with the OpenAI surface. i am using ollama already through OpenCode.

if you hit a specific endpoint that does not work, please file an issue.

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

#107

Earlier quoted context omitted.

Probably just envy.

Obviously it is envy, and not scepticism over a guy who practically lives on Twitter and has unhinged[1] follower base. 1 - https://x.com/__endif/status/2039810651120705569

That's a 404

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

#108
Just to stir thought, I note the TiddlyWiki[1] community (wiki as a self-modifying single html file; 20+ years old) has of course been exploring AI tooling... though not necessarily as an agentic environment. There's a markdown plugin, and others to make the file executable, or into a self-serving web app. Git is more problematic. So hypothetically, one could have a single-file agentic wiki wandering around and self-editing.

[1] https://tiddlywiki.com/

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

#109
The idea seems good, but the system lacks snapshots and data enrichment for each file iteration. If the code breaks or has a bug, the agent could roll back the code and generate enrichment explaining the reason for the rollback, thus generating a new snapshot with updated states. Another issue is the weight of opinion: how will you guarantee integrity and consistency throughout the production of an operating system and avoid collisions and violations of business rules? And regarding persisted memory, currently your system doesn't distinguish between temporal and atemporal memory (business rules, software behaviors and functions, security policies, and governance between agents). The idea is good, but to function as a team, this must also be considered.

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

#110
post #39

Earlier quoted context omitted.

Everyone is writing. Nobody is reading.

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.

I feel like this take misses what LLMs actually bring to the table to a senior developer.

Sure writing code was not the majority of my workday since I moved up in responsibility chain - but that's because I don't get enough uninterrupted time to do the actual coding from all the meetings, syncs, planning, production investigations, mentoring, team activities.

Now that I can delegate code writing to LLM instead of mid/junior devs the dynamics of those tasks change dramatically. The overhead of managing more junior devs is completely gone and no need to have soft skills with an LLM. And communication/iteration speed with LLM is not comparable.

Not to mention I don't need soo much time to get back "into the zone" - LLM can keep working through my meeting - when I'm back it's already working on something and I can quickly get back into the gist of it - much faster than before when I had to take a break and lost all context of what I was doing an hour later. LLM has all that context + more progress right there.

After soo many years of dev I have a pretty good idea of what I want the code to look like - no need to debate the overzealous mid dev about his over abstracted system that's going to haunt me in a production outage next month when we both forgot what he put in - I simply get to say "this is shit rewrite it how I requested". No need to "talk about latest lib that's all the rage on the YouTube blogs etc."

Sure sometimes I realize that doing stuff without LLM would have taken less time - but when I consider how many interruptions I have between my coding sessions - LLMs are empowering precisely because I get to dedicate so little time to my code.

Also less teammates means less communication overhead.

Post reply on HN