Andrej Karpathy on Twitter / X

Andrej Karpathy on Twitter / X

LLM Knowledge BasesSomething I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating…— Andrej Karpathy (@karpathy) April 2, 2026

The REAL Second Brain: an autonomous, self-hosted knowledge wiki that runs on cheap local models

How I turned Karpathy's "LLM wiki" sketch into a system that actually maintains itself — no frontier API, no human in the loop, nothing leaving my LAN.

The rebel alliance

This blog is co-authored with Zoe Weinberg and Matt Hawes at ex/ante, and is a follow-up to our first blog post on the topic, 'You don't own your memory.' We need an open architecture that puts us in control of our memories while making their exploitation technically impossible. But how will this shift happen? In order to discover possible implementations, we must understand how our data informs LLMs. The three predominant context engineering techniques are prompt design, retrieval-augmented ...

Karpathy's LLM Wiki as Agent Memory - Agentic AI Foundation (AAIF)

At work, I’m building agents to handle various operational tasks and have found Karpathy’s LLM Wiki design to be an excellent solution for implementing most ty…

LLM Knowledge Bases

A visual breakdown of Andrej Karpathy's approach to building personal knowledge bases powered by LLMs. Learn the 4-phase pipeline: ingest, compile, query, and maintain - with an interactive architecture diagram.

MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models

Large Language Models (LLMs) have emerged as foundational infrastructure in the pursuit of Artificial General Intelligence (AGI). Despite their remarkable capabilities in language perception and generation, current LLMs fundamentally lack a unified and structured architecture for handling memory. They primarily rely on parametric memory (knowledge encoded in model weights) and ephemeral activation memory (context-limited runtime states). While emerging methods like Retrieval-Augmented Generation (RAG) incorporate plaintext memory, they lack lifecycle management and multi-modal integration, limiting their capacity for long-term knowledge evolution. To address this, we introduce MemOS, a memory operating system designed for LLMs that, for the first time, elevates memory to a first-class operational resource. It builds unified mechanisms for representation, organization, and governance across three core memory types: parametric, activation, and plaintext. At its core is the MemCube, a standardized memory abstraction that enables tracking, fusion, and migration of heterogeneous memory, while offering structured, traceable access across tasks and contexts. MemOS establishes a memory-centric execution framework with strong controllability, adaptability, and evolvability. It fills a critical gap in current LLM infrastructure and lays the groundwork for continual adaptation, personalized intelligence, and cross-platform coordination in next-generation intelligent systems.

Sentient OS - Proactive Intelligence with on-device AI

An on-device LLM understands your entire life, then proactively offers to get your work done through computer use. Private by design. Free and open source.

Supermemory

The memory layer for AI agents. Context engineering platform powering enterprise APIs, developer plugins, and a personal app that remembers everything.

Pieces | Infinite Artificial Memory for your Digital Workers and Agents

Pieces is your AI companion that captures live context from browsers to IDEs and collaboration tools, manages snippets and supports multiple llms - all while processing data locally for maximum control.

Solving a Million-Step LLM Task with Zero Errors

LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans,...

Awni Hannun on Twitter / X

I love this line of research from my colleagues at Apple:Augmenting a language model with a hierarchical memory makes perfect sense for several reasons:- Intuitively the memory parameters should be accessed much less frequently than the weights responsible for reasoning. You… https://t.co/q7HQnYmdR4 pic.twitter.com/38b9q7YKCe— Awni Hannun (@awnihannun) October 6, 2025

Understanding Multimodal LLMs

An introduction to the main techniques and latest models

Compiling knowledge, not retrieving it: a hands-on deep dive into llm-wiki-compiler

The thesis of this piece is simple and uncomfortable: the problem of making an LLM “remember” what you’ve read isn’t solved with more…

On thinking machines

While Chiron Codex is about the application of LLMs and AI-augmented tools, we also need to understand their meaning to us, each other, and society. I have three topics: intelligence,...