A simple message fabric for AI agent sessions

🕹️ Is this the smallest language model in the world? I just managed to squeeze real artificial intelligence into 30 kilobytes, running on a 1979 Atari 800. A fully generative, deterministic languag…

AI agents running research on single-GPU nanochat training automatically

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

Optimize prompts, code, and more with AI-powered Reflective Optimization

A lightweight text-to-speech model with zero-shot voice cloning

Open-source CUDA, Triton and HIP compiler targeting multiple GPU and CPU architectures.

High-efficiency LLM inference engine in C++/CUDA. Run Llama 70B on RTX 3090.

The open-source AI voice studio. Clone, dictate, create.

[CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models

Voxtral ASR & TTS running natively and in the browser. A Rust implementation of Mistral's Voxtral mini realtime ASR / TTS using the Burn ML framework

A LLM trained only on data from certain time periods to reduce modern bias

Synthetic data for computer vision. An open source toolkit using Blender and Python.

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Official inference framework for 1-bit LLMs

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Grandmaster-Level Chess Without Search

Box64 - Linux Userspace x86_64 Emulator with a twist, targeted at ARM64, RV64 and LoongArch Linux devices

CUDA accelerated rasterization of gaussian splatting

[3DV'25 Award Candidate] 3D Reconstruction with Spatial Memory

CUDA accelerated rasterization of gaussian splatting

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small langua…

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Simple MPL-2.0-licensed C++ geometry processing library.

Python bindings for xatlas

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

Instant neural graphics primitives: lightning fast NeRF and more