Repositories list

• OpenETA

  Public
  openeta: embodied task agent

  agentvlawam+ 6

  agentvlawamembodied-artificial-intelligenceembodied-agentembodied-aiembodied-intelligenceembodied-agentsphysical-ai

  Python

  •

  Apache License 2.0

  •22 forks•1919 stars•00 issues•00 pull requests•Updated Jul 29, 2026Jul 29, 2026

• SummerQuest-2026

  Public
  Python

  •5858 forks•66 stars•00 issues•55 pull requests•Updated Jul 29, 2026Jul 29, 2026

• Awesome-WAM

  Public
  A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.

  HTML

  •

  MIT License

  •3030 forks•1.2k1.2k stars•11 issue•4545 pull requests•Updated Jul 29, 2026Jul 29, 2026

• OmniVAE

  Public
  OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

  audiovideodit+ 5

  audiovideoditvideo-generationvaesaudio-generationmultimodal-generationaudio-video-generation

  Python

  •

  Apache License 2.0

  •22 forks•6161 stars•00 issues•00 pull requests•Updated Jul 29, 2026Jul 29, 2026

• Llamascopium

  Public
  Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.

  sparse-autoencodersinterpretabilitysparse-dictionary+ 1

  sparse-autoencodersinterpretabilitysparse-dictionarymechanistic-interpretability

  Python

  •2929 forks•224224 stars•88 issues•00 pull requests•Updated Jul 28, 2026Jul 28, 2026

• AgentHPOBench

  Public
  Python

  •

  Apache License 2.0

  •00 forks•22 stars•00 issues•00 pull requests•Updated Jul 27, 2026Jul 27, 2026

• OmniVAE.github.io

  Public
  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Jul 27, 2026Jul 27, 2026

• MOSS-TTSD

  Public
  MOSS-TTSD is a spoken dialogue generation model designed for expressive multi-speaker synthesis. It features long-context modeling, flexible speaker control, a…

  streamingfinetunetext-to-speeh+ 3

  streamingfinetunetext-to-speehlarge-language-modelssglangspeech-dialogue-generation

  Python

  •

  Apache License 2.0

  •135135 forks•1.4k1.4k stars•5353 issues•00 pull requests•Updated Jul 26, 2026Jul 26, 2026

• MOSS-TTS-Nano

  Public
  MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for real…

  multilingualrealtimetts+ 6

  multilingualrealtimettsenglishchinesestreaming-audiomulti-modalityvoice-cloneaudio-tokenizer

  Python

  •

  Apache License 2.0

  •514514 forks•4k4k stars•1313 issues•66 pull requests•Updated Jul 26, 2026Jul 26, 2026

• MOSS-TTS

  Public
  MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressive…

  audiotext-to-speechmultimodal+ 3

  audiotext-to-speechmultimodalvoice-cloningllmaudio-tokenizer

  Python

  •

  Apache License 2.0

  •349349 forks•3.9k3.9k stars•1212 issues•11 pull request•Updated Jul 26, 2026Jul 26, 2026

• MOSS-Transcribe-Diarize

  Public
  MOSS-Transcribe-Diarize 0.9B is an open-source SOTA end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and…

  Python

  •

  Apache License 2.0

  •7070 forks•1.3k1.3k stars•1111 issues•44 pull requests•Updated Jul 24, 2026Jul 24, 2026

• MOSS-VL

  Public
  MOSS-VL is the core multimodal model series within the OpenMOSS ecosystem, dedicated to visual understanding.

  visionstreaming-videovideo-understanding+ 10

  visionstreaming-videovideo-understandingvlmvision-languagellmsvision-language-modellong-video-understandingreal-time-aivision-language-models+ 3

  Python

  •

  Apache License 2.0

  •1212 forks•404404 stars•22 issues•00 pull requests•Updated Jul 23, 2026Jul 23, 2026

• OpenMOSS.github.io

  Public
  HTML

  •00 forks•22 stars•00 issues•00 pull requests•Updated Jul 18, 2026Jul 18, 2026

• MOSS-Video-Preview

  Public
  A real-time video understanding foundation model with gated cross-attention. Offline & real-time inference.

  Python

  •

  Apache License 2.0

  •44 forks•165165 stars•00 issues•00 pull requests•Updated Jul 16, 2026Jul 16, 2026

• .github

  Public
  00 forks•00 stars•00 issues•00 pull requests•Updated Jul 11, 2026Jul 11, 2026

• claude-codex-handoff

  Public
  Drop-in async file-based handoff protocol for two AI coding agents (Claude Code + Codex), installed as one shared .handoff/ in your project.

  opencodehandoffcodex+ 4

  opencodehandoffcodexai-agentsagent-collaborationclaude-codeclaude-skill

  Python

  •

  MIT License

  •11 fork•3030 stars•00 issues•00 pull requests•Updated Jul 4, 2026Jul 4, 2026

• MOVA

  Public
  MOVA: Towards Scalable and Synchronized Video–Audio Generation

  multimodaldiffusion-modelssglang+ 1

  multimodaldiffusion-modelssglangvideo-audio-generation

  Python

  •

  Apache License 2.0

  •9090 forks•1.1k1.1k stars•2929 issues•11 pull request•Updated Jun 18, 2026Jun 18, 2026

• MOSS-Audio-Tokenizer-Eval

  Public
  Python

  •

  Apache License 2.0

  •00 forks•1111 stars•00 issues•00 pull requests•Updated Jun 16, 2026Jun 16, 2026

• MOSS-Audio-Tokenizer

  Public
  MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming an…

  audiomusictokenizer+ 4

  audiomusictokenizerspeechttsunifiedspeech-representation

  Python

  •

  Apache License 2.0

  •1818 forks•248248 stars•44 issues•11 pull request•Updated Jun 16, 2026Jun 16, 2026

• FRoM-W1

  Public
  [arXiv 26] FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

  whole-body-controlg1humanoid-robots+ 6

  whole-body-controlg1humanoid-robotsh1motion-generationfoundation-modelstext-to-motionunitreefftai

  Python

  •

  Apache License 2.0

  •88 forks•182182 stars•33 issues•00 pull requests•Updated Jun 5, 2026Jun 5, 2026

• MOSS-Audio

  Public
  MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoning in real-world scenar…

  Python

  •4242 forks•620620 stars•1818 issues•00 pull requests•Updated Jun 2, 2026Jun 2, 2026

• MOSS

  Public
  An open-source tool-augmented conversational language model from Fudan University

  natural-language-processingdeep-learningtext-generation+ 3

  natural-language-processingdeep-learningtext-generationdialogue-systemslarge-language-modelschatgpt

  Python

  •

  Apache License 2.0

  •1.1k1.1k forks•12k12k stars•236236 issues•66 pull requests•Updated May 27, 2026May 27, 2026

• sglang

  Public
  Python

  •

  Apache License 2.0

  •00 forks•44 stars•00 issues•00 pull requests•Updated May 12, 2026May 12, 2026

• MOSS-VL-Demo

  Public
  Vue

  •00 forks•66 stars•00 issues•00 pull requests•Updated May 11, 2026May 11, 2026

• MOSS-Music

  Public
  MOSS-Music is an open-source music understanding model for targeting musical captioning, lyrics ASR, structural analysis, chord / key / tempo reasoning, and lon…

  Python

  •1010 forks•125125 stars•33 issues•11 pull request•Updated May 9, 2026May 9, 2026

• MOSS-TTS-Nano-Reader

  Public
  JavaScript

  •55 forks•5353 stars•00 issues•00 pull requests•Updated May 7, 2026May 7, 2026

• mlx-audio

  Public
  A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Sil…

  Python

  •

  MIT License

  •680680 forks•66 stars•00 issues•00 pull requests•Updated Apr 27, 2026Apr 27, 2026

• MOSS-TTS-Nano-Demo

  Public
  CSS

  •22 forks•33 stars•00 issues•00 pull requests•Updated Apr 13, 2026Apr 13, 2026

• llama.cpp

  Public
  C++

  •

  MIT License

  •44 forks•55 stars•00 issues•22 pull requests•Updated Apr 8, 2026Apr 8, 2026

• BandPO

  Public
  Official implementation of BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning. BandPO replaces canoni…

  Python

  •

  GNU General Public License v3.0

  •33 forks•4949 stars•00 issues•00 pull requests•Updated Apr 8, 2026Apr 8, 2026