Hacker News

Show HN: 10x better performance from the Coding Harnesses with LLM-wiki

14 points by nvk ago | 13 comments

xnx |next [-]

Some say text files work even better: https://cloud.google.com/blog/products/data-analytics/how-th...

superfrank |next |previous [-]

I've got a couple of LLM wikis running for different purposes. I just pointed Claude at Karpathy's Github Gist and said "do this" and it set up and has maintained them ever since. So far no issue with that.

Can you explain why the version linked is better?

Gist link: https://gist.github.com/karpathy/442a6bf555914893e9891c11519...

jarbus |next |previous [-]

Where is this 10x number coming from?

dominotw |root |parent |next [-]

from llm wiki

throwaway613746 |root |parent |next |previous [-]

[dead]

esafak |root |parent |previous [-]

The 10x coder who wrote it: https://www.youtube.com/watch?v=d2BuP7-m5Ww

dolebirchwood |next |previous [-]

What if I only want 6x better performance? Is there a knob or slider to dial it down?

adithyassekhar |next |previous [-]

Edit: On closer look this looks useful without the coding harness pitch.

nvk |root |parent [-]

This is not a product, its a foss lib

sppfly |next |previous [-]

This kind of llm bragging title and AI generated webpage makes me gross.

esafak |previous [-]

How does this differ from https://context7.com/ ?

kordlessagain |root |parent [-]

LLM Wiki is client-side and local-first (plain Markdown, Obsidian-friendly) designed for deep multi-agent topic research (e.g. automated thesis/counter-thesis runs, local session memory redaction).

Context7 is a hosted SaaS/on-premise MCP server indexing API/library docs (GitHub, Confluence, OpenAPI) to provide coding assistants with fresh, version-specific developer context.

Essentially: LLM Wiki compiles topic research vaults on your local disk, whereas Context7 acts as a semantic doc/API search gateway for programming.

esafak |root |parent [-]

So the benefit is in caching the resources to avoid web queries, and massaging them to make them amenable to analysis? For intellectual work I imagine it would be useful if it could access gated content, like commercial reports?

kordlessagain |root |parent [-]

Right, it's the whole search pipeline problem defined. Check this out: https://github.com/deepbluedynamics/lume