Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

ACL 2026 - Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control

Official implementation of YingMusic-SVC.

The absolute trainer to light up AI agents.

MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.

Adapting VLMs to Bench2Drive.

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions.…

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient Multi-head Latent Attention Kernels

Integrate the DeepSeek API into popular software

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Code implementation of the paper accepted by IEEE TKDE2024: "Make Heterophilic Graphs Better Fit GNN: A Graph Rewiring Approach"

Dataset and code of GTSinger(NeurIPS 2024 Spotlight): A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Muzic: Music Understanding and Generation with Artificial Intelligence

Use API to call the music generation AI of suno.ai, and easily integrate it into agents like GPTs.

Contrastive Language-Audio Pretraining

Audio generation using diffusion models, in PyTorch.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

Repo for the IDESSAI 2024 course on modeling audio with discrete tokens.

🙃 A delightful community-driven (with 2,500+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python…