Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.

Verified Optimizing Compiler for Cryptographic Primitives

Python library for infinite and infinitesimal numbers using Levi-Civita fields with PyTorch integration

Physical Operations Platform

VIGA: Vision-as-Inverse-Graphics Agent

Design circuit boards with code! ✨ Get software-like design reuse 🚀, validation, version control and collaboration in hardware; starting with electronics ⚡️

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

EGGROLL in C, integer-only training of a language model directly on the CPU

[CVPR 2026 Highlight, the CVPR Compute Gold Star] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

Go monorepo for a framework to build Linux block devices in userspace

S0i3 on FreeBSD (replacement to S3).

Unofficial implementation of Tiny Recursive Model (TRM), improvement to HRM from Sapient AI, by Alexia Jolicoeur-Martineau

A novel data compression framework

🤖 Complete reproduction of 'AlphaGo Moment for Model Architecture Discovery' using MLX-LM instead of GPT-4. Autonomous neural architecture discovery with local LLM inference on Apple Silicon.

MLX-GUI MLX Inference Server for Apple Silicone

a free and opensource app that lets you gain an unfair advantage

Newelle - Your Ultimate Virtual Assistant

The official implementation of "Self-play LLM Theorem Provers with Iterative Conjecturing and Proving"

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

The native Clojure dialect hosted on LLVM with seamless C++ interop.

Homemade automated solar concentrator 🔧 ☀️ 🔎

Code for replicating the experiments reported on in Unexpected Benefits of Self-Modeling in Neural Systems

tl/dw (Too Long, Didn't Watch): Your Personal Research Multi-Tool - a naive attempt at 'A Young Lady's Illustrated Primer' (Open Source NotebookLM)

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

LLM training in simple, raw C/CUDA

FastMLX is a high performance production ready API to host MLX models.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

Scrape the webpage convert it into Markdown, and enhance AI search applications.