A learnable, configurable, and pluggable Omni-Avatar Assistant framework built on LiveKit, featuring real-time interaction, multimodal memory, user persona, and external tool integration.

Docs, Tutorials & ResourcesRAGMultimodal

VIEW DETAILS →

A production-ready implementation of InvisPose that enables real-time, camera-free full-body tracking through walls using commodity WiFi mesh routers and CSI signals, with advanced analytics like fall detection and multi-person tracking.

MultimodalDeep LearningDocker

VIEW DETAILS →

A GPT-powered video retrieval and streaming agent that enables developers to upload multiple videos, search across content in real-time, generate summarized text answers through RAG, and publish searchable collections on the ChatGPT store.

Agent & ToolingPythonFlask

VIEW DETAILS →

An intelligent agent system designed to process and display 4K video content, offering high-quality video processing capabilities.

Agent & ToolingPythonAI Agents

VIEW DETAILS →

A video content discovery tool developed by Microsoft that uses deep learning technology to automatically identify and extract key content from videos, helping users efficiently browse and understand video information。

Agent & ToolingPythonPyTorch

VIEW DETAILS →

Nekro Agent is an extensible multi-person interactive agent framework that combines code execution capabilities with high extensibility, featuring sandbox-driven architecture, visual interface, and multimodal interaction support across multiple platforms.

Agent & ToolingPythonDocker

VIEW DETAILS →

LLaVA-Plus is a multimodal assistant system that learns to use tools, combining large language models with visual capabilities to enable AI agents to perform general vision tasks.

Model & Inference FrameworkPythonPyTorch

VIEW DETAILS →

A groundbreaking visual AI development environment for building no-code data pipelines and multimodal agents with real-time capabilities, social connectors, and AI-powered tools.

Agent & ToolingDockerPostgreSQL

VIEW DETAILS →

OSWorld is a benchmarking platform for evaluating multimodal agents' capabilities in performing open-ended tasks within real computer environments. It supports multiple virtualization platforms including VMware, VirtualBox, Docker, and AWS, offering diverse task scenarios and comprehensive evaluation metrics.

Agent & ToolingPythonDocker

VIEW DETAILS →

A comprehensive platform to generate, animate and schedule AI characters with automated workflows for training LoRA models, creating images/videos, and publishing to social media.

Agent & ToolingNest.jsNext.js

VIEW DETAILS →