Starred repositories
ARC-AGI-3 competition: all 25 game environments
Lightweight, open-source AI agent for your tools, chats, and workflows.
Fully open data curation for reasoning models
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
The first AI that can earn its own existence, replicate, and evolve — without needing a human
llama.cpp fork with additional SOTA quants and improved performance
Database-Backed Durable Python Workflows
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
NviWatch: A blazingly fast rust based TUI for managing and monitoring NVIDIA GPU processes
Connecting KiCad projects with useful tools, on the web!
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
llama3 implementation one matrix multiplication at a time
A non-exhaustive list of details that make a good web interface.
CeTZ: ein Typst Zeichenpaket - A library for drawing stuff with Typst.
Knowledge Agents and Management in the Cloud
A terminal application to view, tail, merge, and search log files (plus JSONL).
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
A collection of GPT system prompts and various prompt injection/leaking knowledge.