AgentENV (AENV) is a distributed platform for running agent environments at scale.

[ICML 2026] Twins: Learn to Predict Unified Representations with Focal Loss

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

[CVPR 2026] Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation

Game engine for 2D and 3D projects with entity component system (ECS) and data-oriented design

JAX in JavaScript – ML library for the web, running on WebGPU & Wasm

Ming-omni-tts: Simple and Efficient Unified Generation of Speech, Music, and Sound with Precise Control

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…

MCP Server for Ghidra

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

A hive mind communication platform

Implementation for "Statistically-Lossless Quantization of Large Language Models"

Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

OmniVoice TTS nodes for ComfyUI - Zero-shot multilingual text-to-speech with voice cloning, voice design, and multi-speaker dialogue

Open-source Dreamer world-model implementation in JAX

A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterb…

Local AI text-to-speech with voice cloning and voice design, powered by GGML. C++17 port of OmniVoice (k2-fsa/OmniVoice). 646 languages, 24 kHz mono output, runs on CPU, CUDA, ROCm, Metal, Vulkan.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Real-time text-to-speech with Qwen3-TTS

zero-shot voice conversion & singing voice conversion, with real-time support

The world's first agentic reverse engineer.

Open-source AI reverse-engineering agent using Ghidra and LLMs to reconstruct and validate C/C++ functions from binaries.

Official Pytorch implementation for "Twisted Schrödinger Bridge Matching"

LLM inference in C/C++