Thinh Le Claim this profile

A Vietnamese Voice Cloning Text-to-Speech Model ✨

A terminal workspace with batteries included

A high-throughput and memory-efficient inference and serving engine for LLMs (Windows build & kernels)

Open Source Computer Vision Library

A straightforward method for training your LLM, from downloading data to generating text.

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.

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1× and 2× cards.

ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

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

Animation engine for explanatory math videos

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, OpenClaw, Factory Droid, Trae, Google Antigravity). Turn any folder of code, docs, papers, images, or videos into a queryable knowledge graph

A browser-based 3D CAD application for online model design and editing

The KiCAD web viewer

This is an active mirror of the KiCad development branch, which is hosted at GitLab (updated every time something is pushed). Pull requests on GitHub are not accepted or watched.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

Describe Anything, Anywhere, at Any Moment (DAAAM), a novel approach to real-time, large-scale, spatio-temporal memory

BOM, STL files and instructions for PAROL6 3D printed robot arm

learningggggggg 🐳

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

No description.

Latent Spatial Memory for Video World Models

The library for web and native user interfaces.

Building AI agents, atomically

Claude Code skills that turn any codebase into an interactive knowledge graph you can explore, search, and ask questions about (Multi-platform e.g., Codex are supported).

A unified framework for easy reinforcement learning in Flow-Matching models

All the source code for "Robot Learning: A Tutorial". Get involved to be featured in the next iteration!

An MCP-based chatbot | 一个基于MCP的聊天机器人

Streamlit — A faster way to build and share data apps.

No description.

Any source (PDF, video, web, audio, text) to interactive learning package with quizzes, flashcards and spaced repetition. One command, 12-section study guide.

On-device AI across mobile, embedded and edge for PyTorch

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

A ready-to-go template for building powerful Agent APIs

🎉 Web component JS frameworks overview by their syntax and features

[CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation

A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents — so you don't have to.

Specifications for OpenTelemetry

No description.

Fast job queuing and RPC in python with asyncio and redis.

An extendable async API using FastAPI, Pydantic V2, SQLAlchemy 2.0, PostgreSQL and Redis.

Production-grade client-side tracing, profiling, and analysis for complex software systems.

The Monorepo Platform that amplifies both developers and AI agents. Nx optimizes your builds, scales your CI, and fixes failed PRs automatically. Ship in half the time.

Find secrets with Gitleaks 🔑

⚙️ A curated list of static analysis (SAST) tools and linters for all programming languages, config files, build tools, and more. The focus is on tools which improve code quality.

Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.

Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Continuous Inspection

Browser automation CLI for AI agents

Typer, build great CLIs. Easy to code. Based on Python type hints.

A modern animation library for React and JavaScript

Real-time stream editing pipeline powered by the FLUX.2-klein-4B model, optimized for consumer GPUs

⚡ Serverless Framework – Effortlessly build apps that auto-scale, incur zero costs when idle, and require minimal maintenance using AWS Lambda and other managed cloud services.

Cook up amazing multimodal AI applications effortlessly with MiniCPM-o

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

#1 Persistent memory for AI coding agents based on real-world benchmarks

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

Open source video conferencing app powered by LiveKit. Built with Django and React.

Architecture decision record (ADR) examples for software planning, IT leadership, and template documentation

Standard Go Project Layout

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

🔎 Open source distributed and RESTful search engine.

OpenFeature specification

A flexible distributed key-value database that is optimized for caching and other realtime workloads.

[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

No description.

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Rerun viewer with Gradio

State-of-the-art 2D and 3D Face Analysis Project

The world's simplest facial recognition api for Python and the command line

Universal memory layer for AI Agents

Memory for 24/7 proactive agents like OpenClaw.

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

Understanding Deep Learning - Simon J.D. Prince

Build, enrich, and transform datasets using AI models with no code

Proof-of-concept time-travel debugger for the Bevy game engine, built using Rerun.

lakeFS - Data version control for your data lake | Git for data

Custom ComfyUI nodes for game developers. Includes Hunyuan 3D 2.1 for 3D asset generation and Ollama prompt extender for enhanced AI prompting workflows.

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Production-grade MCP server and AI tools for the Godot engine. A Snap to install. Totally free and fun.

A modern load testing tool, using Go and JavaScript

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

A fancy self-hosted monitoring tool

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

OpenTofu lets you declaratively manage your cloud infrastructure.

No description.

v1 of Asimov, an open-source humanoid robot

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

Cursor for Minecraft

HY-Embodied: Embodied Foundation Models for Real-World Agents

Backup and migrate Kubernetes applications and their persistent volumes

Open-source framework for holistic, structured repository-level documentation across multilingual codebases

Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.

Interactive Periodic table with 3D atoms

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

OCR model that handles complex tables, forms, handwriting with full layout.

High-Quality Voice Cloning TTS for 600+ Languages

Learn CUDA with PyTorch

Emulate Arduino, ESP32 & Raspberry Pi. in your browser. Write code, compile, and run on 19 real boards — Arduino Uno, ESP32, ESP32-C3, Raspberry Pi Pico, Raspberry Pi 3, and more. No hardware, no cloud, no limits.. Discord: https://discord.gg/3mARjJrh4E

Learn how to train a quadruped robot to walk using reinforcement learning, from defining actions and observations to designing rewards and transitioning from simulation to reality.

Automated YouTube Shorts pipeline: news → script → AI visuals → voiceover → captions → upload

This repository implements teleoperation of the Unitree humanoid robot using XR Devices.

Hydra is a framework for elegantly configuring complex applications

Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

🔍 Minimal examples of machine learning tests for implementation, behaviour, and performance.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

A Pragmatic VLA Foundation Model

Web-based 3D visualization in Python

Beads - A memory upgrade for your coding agent

A comprehensive toolkit for reliably locking, packing and deploying environments for ComfyUI workflows.

A collection of guides and examples for the Gemma open models from Google.

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

An open source trusted cloud native registry project that stores, signs, and scans content.

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

An Open Source implementation of Notebook LM with more flexibility and features

✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】

The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.

MobileGaze: Real-Time Gaze Estimation models using ResNet 18/34/50, MobileNet v2 and MobileOne s0-s4 | In PyTorch >> ONNX Runtime Inference

Memento-Skills: Let Agents Design Agents

This is the official repository for TalkSHOW: Generating Holistic 3D Human Motion from Speech [CVPR2023].

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

Foundation Models and Data for Human-Human and Human-AI interactions.

The open source wisprflow alternative

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

No description.

Python inverse kinematics based on MuJoCo.

Unified framework for robot learning built on NVIDIA Isaac Sim

Tien Kung-Lab: Direct IsaacLab Workflow for Legged Robots

Efficient Vietnamese Speech Recognition

No description.

Multi-Joint dynamics with Contact. A general purpose physics simulator.

No description.

Monocular whole-body 3D human pose estimation using the SOMA body model

SOMA BVH to humanoid robot motion retargeting library built with Newton and NVIDIA Warp

A visualization tool of some 3d human models(smpl/smplx/flame), also supports editing models' parameters

This add-on allows you to edit, reshape and animate SMPL-H, SMPL-X, and SUPR bodies ("SMPL Bodies" for short) to your current Blender scene. Each body consists of a mesh, a shape specific skeleton, and blendshapes (also known as "shape keys") for body shape, facial expressions and pose correctives.

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

SOMA: Unifying Parametric Human Body Models

Apache Flink

Google's Agent-to-Agent (A2A) protocol with Apache Kafka using Spring Boot.

Examples for Cerebrium Serverless GPUs

Apache Kafka - A distributed event streaming platform

A curated list of full-duplex spoken dialogue models

[NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory

A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related websites.

Autonomous robot implemented for finding shortest path in an artificial city

A web application for browsing and viewing the BONES-SEED motion capture dataset

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.

Build, run, manage agentic software at scale.

3D force-directed graph component using ThreeJS/WebGL

An example showing how to do different kinds of AI agents with Temporal in an order repair context

Apache Superset is a Data Visualization and Data Exploration Platform

A turnkey MLOps pipeline demonstrating how to go from raw events to real-time predictions at scale.

To simplify and streamline LLM operations, empowering developers and organizations to harness the full potential of large language models with ease.

Face Recognition Web application Login with liveness detection for Anti-Spoofing

"1 config, 1 command from Jupyter Notebook to serve Millions of users", Full-stack On-Premises MLOps system for Computer Vision from Data versioning to Model monitoring and drift detection.

Use AI Agents directly in Blender.

Automate the process of making money online.

Virtual whiteboard for sketching hand-drawn like diagrams

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

very good whiteboard infinite canvas SDK

This project is an implementation of the paper from Google Research: DS-STAR: A State-of-the-Art Versatile Data Science Agent.

Real-time speech translation — macOS & Windows, free TTS, no server, your API keys only

The world's first open-source multimodal creative assistant This is a substitute for Canva and Manus that prioritizes privacy and is usable locally.

🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

A progressive Node.js framework for building efficient, scalable, and enterprise-grade server-side applications with TypeScript/JavaScript 🚀

The beautiful & flexible React.js docs framework.

Open-source vector similarity search for Postgres

The fantastic ORM library for Golang, aims to be developer friendly

The React Framework

ClickHouse® is a real-time analytics database management system

Deep Agents in JS

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

Open Agent Spec (Agent Spec) is a framework-agnostic declarative language for defining agentic systems. It defines building blocks for standalone agents and structured agentic workflows as well as common ways of composing them into multi-agent systems.

Here, CLI tools, libraries, Add-ons, Reports, Benchmarks and Sample Scripts for taking advantage of Google Apps Script which are publishing in my blog, Gists and GitHub are summarized.

:fire: 2D and 3D Face alignment library build using pytorch

React Flow | Svelte Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev) or Svelte (https://svelteflow.dev). Ready out-of-the-box and infinitely customizable.

Self-serve BI to 10x your data team ⚡️

An open-source SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skills and subagents, it handles different levels of tasks that could take minutes to hours.

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

🎓 Update Talking-Face Research Papers Daily

Create your own playable 2D characters and maps, powered by fal.ai

Debug your AI agents

[Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

MPFB2 is a free and open source human generator for Blender

Bella is best

Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google

No description.