Local voice dictation for mac, windows and linux

Fast Robot Kinematics and Dynamics in JAX

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…

LLM Inference Engine for Metal, CUDA and Vulkan.

🌍 WorldGen - Generate Any 3D Scene in Seconds

Pika H3 Flex: video and audio generation inference

PhysAg3D: Bridging 3D Generative and Agentic Models for High-Fidelity and Physically-Interactive Assets

RDNA-native LLM inference engine in Rust.

SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.

The official repository for Embodied.cpp.

AgentGarten: Code Worlds for Evolving Agents

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST.…

Generate Mujoco environments from natural language

Turn your coding agents into research agents

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

AI agents running research on single-GPU nanochat training automatically

A modular embodied-agent runtime for RoboTwin, combining VLM-based grounding, subgoal scheduling, OpenPI/pi0.5 action generation, and execution-time verification.

An open-source collection of embedded development and debugging skills for Claude Code, Copilot, TRAE, and other AI coding assistants that support the Skill protocol. Once installed, the AI assista…

A simulation benchmarking platform for evaluating generalist robot policies

Cross-vendor 3D Gaussian Splatting trainer - video to splat to mesh, Vulkan or CUDA.

This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent…

Just a VLM Agent Can Play Robots

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

FOLOTOY AI Passport develop resources for Agent

DeepSeek Harness Host plugin for h3-hip.c (--serve, protocol v1alpha)

Reinforcement learning Lab of Microduck with ROCm

the runtime your coding agents live on