Lists (2)
Starred repositories
High-Quality Voice Cloning TTS for 600+ Languages
Write HTML. Render video. Built for agents.
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video pro…
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
One dashboard. An entire research team.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and…
Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
A framework for efficient model inference with omni-modality models
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Examples and guides for using the Gemini API
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
🚀 Efficient implementations for emerging model architectures
A high-level multi-agent development framework built on LangGraph, combining CrewAI’s intuitive concepts with enterprise-grade features, ready-to-use templates, and full-stack UI for rapid producti…
SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.
The official implement of VITA, VITA15, LongVITA, VITA-Audio, VITA-VLA, and VITA-E.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.