Stars
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Build and install script for llama.app
A small, powerful, open-source CLI coding agent that works with open models.
djbsort: fast, data-oblivious sorting algorithm.
Reference implementation of "Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation" (Heinsen and Kozachkov, 2026)
Lightweight coding agent that runs in your terminal
HMLL - High-Performance Model Loading Library for Efficient AI Model I/O
Statically-linked clang distribution. Uses musl libc on Linux and only depends on libSystem on OSX
UltraCDC, a fast content-defined chunking algorithm for data deduplication.
Small library allowing to use dlopen() from statically-linked applications (where statically-linked executable vs loaded shared library may use completely different libc's)
Inference server benchmarking tool
🤗 smolagents: a barebones library for agents that think in code.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Minimalistic 4D-parallelism distributed training framework for education purpose
Large Language Model Text Generation Inference
The financial transactions database designed for mission critical safety and performance.
Tool and library for generating X.509 certificates and certificate requests (mirror)
An ASCII Header Generator for Network Protocols
A minimalist client for sending mail direct to recipient's MX