AI agents running research on single-GPU nanochat training automatically
Repository Index
132,241 visible repositories in the index
1–24 of 44 · Most stars
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The best ChatGPT that $100 can buy.
LLM Council works together to answer your hardest questions
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
- claude-code
- obsidian
- second-brain
- claude-code-skill
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspired by Karpathy and 3Blue1Brown for moving beyond prompt engineering to the wider discipline of context design, orchestration, and optimization.
Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.
- healthcare
- llm
- on-device
- on-premise
Web interface for browsing, search and filtering recent arxiv submissions
Video+code lecture on building nanoGPT from scratch
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.
The repository host gives no description.
An autoregressive character-level language model for making more things
A Python module for learning all major algorithms
- algorithms
- data-structures
- python3
- modules
Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
- agent-skills
- knowledge-base
- llm-tools
- obsidian
A Dockerized python Script to fetch Garmin health data and populate that in a InfluxDB Database, for visualization long term health trends with Grafana
- garmin
- garmin-api
- garmin-connect
- garmin-data
Python AutoML toolkit for benchmarking classification, regression, and time-series forecasting models, with GPU acceleration, MLflow tracking, and automated preprocessing.
- machine-learning
- automl
- regression
- classification
The repository host gives no description.
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
- automation
- autonomous-agent
- autoresearch
- codex
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
- agent-skill
- claude-code
- codex
- cursor
Render any git repo into a single static HTML page for humans or LLMs