jart

private-gpt

Interact with your documents using the power of GPT, 100% privately, no data leaks

llm.c

LLM training in simple, raw C/CUDA

web-check

🕵️‍♂️ All-in-one OSINT tool for analysing any website

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

quickjs

Public repository of the QuickJS Javascript Engine.

EASTL

EASTL stands for Electronic Arts Standard Template Library. It is an extensive and robust implementation that has an emphasis on high performance.

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

mergekit

Tools for merging pretrained large language models.

stable-diffusion.cpp

Stable Diffusion in pure C/C++

oasis

a small statically-linked linux system

blis

BLAS-like Library Instantiation Software Framework

SwiftTerm

Xterm/VT100 Terminal emulator in Swift

Decker

A multimedia sketchpad

LLMUnity

Create characters in Unity with LLMs!

typometer

Text / code editor typing latency analyzer

gguf-tools

GGUF implementation in C as a library and a tools CLI program

hermit

Actually Portable WebAssembly compiler toolchain for self-contained cross-platform binaries

cuda-convnet

Alex Krizhevsky's original code from Google Code

scrapscript

A functional, content-addressable programming language.

neuralink_brainwire

Attempt at Neuralink's Compression Challenge

llamafile-rag-example

100-languages

Solving the first 100 Project Euler problems using 100 different programming languages!

cosmopolitan-sdl2

Cosmopolitan-SDL-example

Example of using SDL2 with Cosmopolitan Libc

whisperfile

LocalMentor

Local Startup Advisor Chatbot

nisaba

Create an IRC chat bot powered by AI, using llamafile, in minutes.

llamafile-llamaindex-examples

cosmo_cc_bazel_toolchain

Bazel toolchain that is backed by cosmopolitan

r3

Source code for the Rebol [R3] interpreter