Stars
Real-time webcam demo with SmolVLM and llama.cpp server
Continuous Thought Machines, because thought takes time and reasoning is a process.
aider is AI pair programming in your terminal
🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton
Magical Deterministic Simulator for distributed systems in Rust.
I made my AI think harder by making it argue with itself repeatedly. It works stupidly well.
🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.
A TTS model capable of generating ultra-realistic dialogue in one pass.
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Scenic: A Jax Library for Computer Vision Research and Beyond
A reimplementation of Andrej Karpathy's repository for an RL self-learning AI agent that learns to play Pong through trial and error, using PyTorch
Shadow is a discrete-event network simulator that directly executes real application code, enabling you to simulate distributed systems with thousands of network-connected processes in realistic an…
A roadmap for "generative AI" learning resources
Server ecosystem for Standard Notes; fully self-hostable.
Continuous profiling for analysis of CPU and memory usage, down to the line number and throughout time. Saving infrastructure cost, improving performance, and increasing reliability.
A simple screen parsing tool towards pure vision based GUI agent
Enterprise-ready zero-trust access platform built on WireGuard®.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)