⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

Open-source Dreamer world-model implementation in JAX

ccache – a fast compiler cache

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Language model tokenization at GB/s

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

Box3D is a 3D physics engine for games

slime is an LLM post-training framework for RL Scaling.

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

Official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.

extract all your personal data history from cursor, codex, claude-code, windsurf, and trae

The simplest, fastest repository for training/finetuning medium-sized GPTs.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign languag…

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

Universal AI coding proxy. Use Claude Code, Codex CLI, or any tool with DeepSeek, GLM, MiniMax, and more—without rate limits breaking your flow.

Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

Control panel for VLLM, Sglang, llama.cpp, exllamav3

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

If tinygrad wasn't small enough for you...

Overworld's local world client interface to run Waypoint world models

Repository for the CUDA H100 Course

SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression

Autonomous GPU Kernel Generation & Optimization via Deep Agents

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.