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

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

superfrank 39 minutes ago | parent | prev | next [-]

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 an hour ago | parent | prev | next [-]

Where is this 10x number coming from?

	▲	dominotw an hour ago \| parent \| next [-]
		from llm wiki
	▲	throwaway613746 an hour ago \| parent \| prev \| next [-]
		[dead]
	▲	esafak an hour ago \| parent \| prev [-]
		The 10x coder who wrote it: https://www.youtube.com/watch?v=d2BuP7-m5Ww

▲

dolebirchwood an hour ago | parent | prev | next [-]

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

▲

adithyassekhar an hour ago | parent | prev | next [-]

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

	▲	nvk 42 minutes ago \| parent [-]
		This is not a product, its a foss lib

▲

sppfly an hour ago | parent | prev | next [-]

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

▲

esafak an hour ago | parent | prev [-]

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

▲

kordlessagain an hour ago | 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 40 minutes ago | 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 21 minutes ago \| parent [-]
		Right, it's the whole search pipeline problem defined. Check this out: https://github.com/deepbluedynamics/lume