Skip to content

@stepfun-ai stepfun-ai

Change the repository type filter

All

    Repositories list

    29 repositories

    • SteptronOss

      Public
      A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across S…
      Python
      •
      Apache License 2.0
      •40•558•3•3•Updated Apr 21, 2026Apr 21, 2026

    • StepAudio-Skills

      Public
      Audio skills for Claw
      Python
      •
      Apache License 2.0
      •1•19•0•0•Updated Apr 16, 2026Apr 16, 2026

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •16k•43•0•2•Updated Apr 13, 2026Apr 13, 2026

    • llama.cpp

      Public
      LLM inference in C/C++
      C++
      •
      MIT License
      •17k•2•0•0•Updated Apr 9, 2026Apr 9, 2026

    • Step-Audio-EditX

      Public
      A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust z…
      text-to-speechreinforcement-learningaudio-editing
      text-to-speechreinforcement-learningaudio-editingttscross-lingualvoice-cloningparalinguisticsstyle-controlspeaking-stylezero-shot-tts
      Python
      •
      Apache License 2.0
      •62•907•35•2•Updated Apr 9, 2026Apr 9, 2026

    • Step-3.5-Flash

      Public
      Fast, Sharp & Reliable Agentic Intelligence
      C++
      •
      Apache License 2.0
      •82•2k•12•3•Updated Apr 3, 2026Apr 3, 2026

    • StepDeepResearch

      Public
      Step-DeepResearch
      Python
      •
      Apache License 2.0
      •23•550•3•0•Updated Mar 24, 2026Mar 24, 2026

    • Step-Audio-R1

      Public
      Python
      •
      Apache License 2.0
      •42•643•19•0•Updated Mar 16, 2026Mar 16, 2026

    • Step-Audio2

      Public
      Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.
      Python
      •
      Apache License 2.0
      •101•1.4k•53•2•Updated Mar 16, 2026Mar 16, 2026

    • gelab-zero

      Public
      STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities.
      agentpuagui-agents
      agentpuagui-agentsphone-use-agent
      Python
      •
      MIT License
      •185•2.1k•38•4•Updated Mar 14, 2026Mar 14, 2026

    • NextStep-1

      Public
      [🚀 ICLR 2026 Oral] NextStep-1: SOTA Autogressive Image Generation with Continuous Tokens. A research project developed by the StepFun’s Multimodal Intelligence …
      Python
      •
      Apache License 2.0
      •24•680•0•0•Updated Feb 27, 2026Feb 27, 2026

    • GEBench

      Public
      Python
      •
      Apache License 2.0
      •0•52•0•0•Updated Feb 25, 2026Feb 25, 2026

    • PaCoRe

      Public
      PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
      Python
      •13•336•0•0•Updated Feb 5, 2026Feb 5, 2026

    • StepMesh

      Public
      C++
      •
      Apache License 2.0
      •40•363•10•1•Updated Jan 28, 2026Jan 28, 2026

    • Step3-VL-10B

      Public
      Step3-VL-10B: A compact yet frontier multimodal model achieving SOTA performance at the 10B scale, matching open-source models 10-20x its size.
      Apache License 2.0
      •29•402•16•2•Updated Jan 21, 2026Jan 21, 2026

    • stepfun-ai.github.io

      Public
      HTML
      •0•0•0•0•Updated Jan 13, 2026Jan 13, 2026

    • Step1X-Edit

      Public
      A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
      image-editingreasoningvisual-reasoning
      image-editingreasoningvisual-reasoning
      Python
      •
      Apache License 2.0
      •96•2.2k•31•1•Updated Dec 29, 2025Dec 29, 2025

    • stepfunApi-audio-sdk

      Public
      基于阶跃星辰开放平台语音api的android 语音sdk，支持tts 流式与非流式，asr，流式，非流式音频播放器，语音录制能力
      Kotlin
      •
      Apache License 2.0
      •0•5•0•0•Updated Dec 15, 2025Dec 15, 2025

    • Step-Realtime-Console

      Public
      Step-Realtime-Console
      JavaScript
      •
      Apache License 2.0
      •11•70•3•0•Updated Dec 15, 2025Dec 15, 2025

    • Step-Audio-Edit-Benchmark

      Public
      Python
      •0•18•0•0•Updated Nov 22, 2025Nov 22, 2025

    • Step1X-3D

      Public
      Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
      Python
      •
      Apache License 2.0
      •57•860•38•2•Updated Sep 8, 2025Sep 8, 2025

    • StepFun-Formalizer

      Public
      StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion
      Python
      •
      Apache License 2.0
      •2•25•0•0•Updated Aug 19, 2025Aug 19, 2025

    • StepFun-Prover-Preview

      Public
      Large language models designed for formal theorem proving through tool-integrated reasoning.
      Apache License 2.0
      •0•34•0•0•Updated Aug 13, 2025Aug 13, 2025

    • Step3

      Public
      Apache License 2.0
      •11•453•4•1•Updated Aug 10, 2025Aug 10, 2025

    • InfiniteHBD-Trace

      Public
      Apache License 2.0
      •0•17•0•0•Updated May 21, 2025May 21, 2025

    • Step-Realtime-Python-Demo

      Public
      Step Realtime Demo
      Python
      •0•3•0•0•Updated May 6, 2025May 6, 2025

    • ComfyUI-StepVideo

      Public
      Python
      •
      MIT License
      •5•43•1•2•Updated Mar 27, 2025Mar 27, 2025

    • Step-Video-TI2V

      Public
      Python
      •
      MIT License
      •35•376•5•1•Updated Mar 20, 2025Mar 20, 2025

    • Step-Video-T2V

      Public
      Python
      •
      MIT License
      •335•3.2k•40•6•Updated Mar 17, 2025Mar 17, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.