Foundation

I Built a Knowledge Base That Writes Itself. Here Is What Andrej Karpathy Got Right.

Andrej Karpathy posted about using LLMs to build personal knowledge bases. I took his workflow, wired it into my Obsidian vault with Claude Code, and within an hour had 21 cross-linked wiki articles compiled from YouTube transcripts. Here is how it works and why it matters.

How to Build an LLM Knowledge Base

A hands-on guide to building a simple LLM knowledge base with raw markdown sources, a compiled wiki, reusable prompts, and an agent that keeps improving the knowledge base over time.

Modal Foundation

Supporting decentralized social tech and open standards to create trustworthy, public-interest social media alternatives and ensure access to vital information.

Typst: The new foundation for documents

Typst is the new foundation for documents. Sign up now and experience limitless power to write, create, and automate anything that you can fit on a page.

Outline – Team knowledge base & wiki

A modern team knowledge base for your internal documentation, product specs, support answers, meeting notes, onboarding, & more…

Announcing the Modal Foundation - Updates from the Modal Foundation

We're a nonprofit dedicated to supporting decentralized social technologies that help people create, circulate and discover trustworthy information.

Social Web Foundation

Towards a bigger, better fediverse

LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory

LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory · GitHub

Wiki Builder: A Claude Code Plugin for Building LLM Knowledge Bases

Wiki Builder is an open-source Claude Code plugin that turns the LLM-knowledge-base workflow into a one-command setup. Scaffold a configurable wiki, point Claude at sources, and let the agent compile durable pages, indexes, and concept maps for you.

DataRater: Meta-Learned Dataset Curation

The quality of foundation models depends heavily on their training data. Consequently, great efforts have been put into dataset curation. Yet most approaches rely on manual tuning of...

Pluralis Research

Protocol Learning — decentralized, communication-efficient model-parallel training for foundation models.

DeepWiki | AI documentation you can talk to, for every repo

DeepWiki provides up-to-date documentation you can talk to, for every repo in the world. Think Deep Research for GitHub - powered by Devin.

elvis on Twitter / X

Building a personal knowledge base for my agents is increasingly where I spend my time these days. Like @karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for… https://t.co/4AQSFOv4PV pic.twitter.com/YI5cWUhqT3— elvis (@omarsar0) April 2, 2026