Skip to content

@OpenMOSS OpenMOSS (SII)

Change the repository type filter

All

    Repositories list

    50 repositories

    • 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
      •562•6•0•0•Updated Apr 24, 2026Apr 24, 2026

    • MOSS-VL

      Public
      MOSS-VL is the core multimodal model series within the OpenMOSS ecosystem, dedicated to visual understanding.
      Python
      •
      Apache License 2.0
      •4•231•0•0•Updated Apr 24, 2026Apr 24, 2026

    • Llamascopium

      Public
      Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
      sparse-autoencodersinterpretabilitysparse-dictionary
      sparse-autoencodersinterpretabilitysparse-dictionarymechanistic-interpretability
      Python
      •28•214•8•0•Updated Apr 20, 2026Apr 20, 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
      •9•168•1•0•Updated Apr 20, 2026Apr 20, 2026

    • MOSS-TTS-Nano-Reader

      Public
      JavaScript
      •4•32•0•0•Updated Apr 17, 2026Apr 17, 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
      multilingualrealtimettsenglishchinesestreaming-audiomulti-modalityvoice-cloneaudio-tokenizer
      Python
      •
      Apache License 2.0
      •299•2.2k•32•4•Updated Apr 17, 2026Apr 17, 2026

    • sglang

      Public
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Apr 14, 2026Apr 14, 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
      audiomusictokenizerspeechttsunifiedspeech-representation
      Python
      •
      Apache License 2.0
      •13•195•3•1•Updated Apr 13, 2026Apr 13, 2026

    • MOSS-TTS-Nano-Demo

      Public
      CSS
      •1•1•0•0•Updated Apr 13, 2026Apr 13, 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
      audiotext-to-speechmultimodalvoice-cloningllmaudio-tokenizer
      Python
      •
      Apache License 2.0
      •154•1.7k•23•1•Updated Apr 13, 2026Apr 13, 2026

    • MOSS-Video-Preview

      Public
      A real-time video understanding foundation model built on Llama-3.2-Vision, featuring comprehensively extended video processing and multimodal reasoning capabil…
      Python
      •
      Apache License 2.0
      •4•136•0•0•Updated Apr 13, 2026Apr 13, 2026

    • MOSS-VL-Demo

      Public
      Vue
      •0•5•0•0•Updated Apr 9, 2026Apr 9, 2026

    • llama.cpp

      Public
      C++
      •
      MIT License
      •2•3•0•2•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
      •4•48•0•0•Updated Apr 8, 2026Apr 8, 2026

    • imclaw-skill

      Public
      Python
      •0•7•0•0•Updated Apr 3, 2026Apr 3, 2026

    • MOVA

      Public
      MOVA: Towards Scalable and Synchronized Video–Audio Generation
      multimodaldiffusion-modelssglang
      multimodaldiffusion-modelssglangvideo-audio-generation
      Python
      •
      Apache License 2.0
      •83•958•27•1•Updated Apr 1, 2026Apr 1, 2026

    • TransformerLens

      Public
      A library for mechanistic interpretability of GPT-style language models
      Python
      •
      MIT License
      •555•2•0•0•Updated Mar 31, 2026Mar 31, 2026

    • Embodied-Planner-R1

      Public
      Embodied-Planner-R1: Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
      Python
      •
      Apache License 2.0
      •1•27•0•4•Updated Mar 30, 2026Mar 30, 2026

    • DiRL

      Public
      Python
      •
      Apache License 2.0
      •7•158•0•1•Updated Mar 30, 2026Mar 30, 2026

    • OurClaw

      Public
      Institutional OpenClaw Solution. Share One Claw with Others.
      TypeScript
      •
      MIT License
      •3•24•0•0•Updated Mar 30, 2026Mar 30, 2026

    • RoboOmni

      Public
      Official code of "RoboOmni: Proactive Robot Manipulation in Omni-modal Context"
      Python
      •5•105•6•0•Updated Mar 28, 2026Mar 28, 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
      streamingfinetunetext-to-speehlarge-language-modelssglangspeech-dialogue-generation
      Python
      •
      Apache License 2.0
      •126•1.3k•52•0•Updated Mar 23, 2026Mar 23, 2026

    • TTSD-eval

      Public
      Python
      •0•4•0•0•Updated Mar 16, 2026Mar 16, 2026

    • OpenMOSS.github.io

      Public
      JavaScript
      •0•2•0•0•Updated Mar 3, 2026Mar 3, 2026

    • Website

      Public
      wangye
      JavaScript
      •3•0•0•1•Updated Mar 2, 2026Mar 2, 2026

    • FRoM-W1

      Public
      [ArXiv 26] FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions
      whole-body-controlg1humanoid-robots
      whole-body-controlg1humanoid-robotsh1motion-generationfoundation-modelstext-to-motionunitreefftai
      Python
      •
      Apache License 2.0
      •7•154•3•0•Updated Feb 13, 2026Feb 13, 2026

    • MOSS-Speech

      Public
      MOSS-Speech is a true speech-to-speech large language model without text guidance.
      voice-assistantspeech-to-speechlarge-language-models
      voice-assistantspeech-to-speechlarge-language-models
      Python
      •
      Apache License 2.0
      •7•130•2•0•Updated Feb 13, 2026Feb 13, 2026

    • RoboJuDo

      Public
      [ArXiv 26] The Depolyment Framework for the FRoM-W1 Project
      Python
      •
      Other
      •63•4•0•0•Updated Jan 28, 2026Jan 28, 2026

    • FutureOmni

      Public
      Python
      •1•22•0•0•Updated Jan 22, 2026Jan 22, 2026

    • ABC-Bench

      Public
      ABC-Bench is a benchmark for Agentic Backend Coding. It evaluates whether code agents can explore real repositories, edit code, configure environments, deploy c…
      2•29•1•0•Updated Jan 20, 2026Jan 20, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.