Code for the ICASSP 2022 paper "Transformer-Based Multi-Aspect Multi-Granularity Non-native English Speaker Pronunciation Assessment".

A small JS library for beautiful drawing and handwriting on the HTML Canvas.

Modern CLI tool for scraping & analyzing Facebook groups using Playwright & Gemini AI. Features self-healing selectors, session security, and local offline analysis.

Hebrew Diacritizer

Hebrew grapheme to phoneme (G2P)

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

MCP server to provide Figma layout information to AI coding agents like Cursor

A TTS model capable of generating ultra-realistic dialogue in one pass.

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Fast drag and drop for any experience on any tech stack

Universal memory layer for AI Agents

Evaluation and Tracking for LLM Experiments and AI Agents

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

The LLM Evaluation Framework

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

JavaScript animation engine

C++ examples for the Vulkan graphics API

high-performance rendering backend (C++, Python, C#, Java)

🎃 Windowless WebGL for node.js

A generative world for general-purpose robotics & embodied AI learning.

Generate 3D objects conditioned on text or images

Cross-platform, graphics API agnostic, "Bring Your Own Engine/Framework" style rendering library.

Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D engine that enables developers and content creators to build AAA games, cinema-quality 3D worlds, and high-fidelity simulations wit…

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Moveable! Draggable! Resizable! Scalable! Rotatable! Warpable! Pinchable! Groupable! Snappable!

💅 Beautiful and accessible drag and drop for lists with React. ⭐️ Star to support our work!

The modern toolkit for building drag and drop interfaces