Bytedance Inc. ORG

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 tasks that could take minutes to hours.

An AI agent framework that orchestrates long-running automation tasks, research, coding, planning, across multiple tools, sub-agents, and memory, deployable via Docker or locally.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

UI-TARS Desktop provides two AI agent tools that let an AI model look at your screen and control browsers or desktop apps by clicking and typing, so you can automate multi-step computer tasks using plain-language instructions.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

An open-source AI coding agent from ByteDance that takes plain-English instructions and autonomously writes code, edits files, and runs commands on your project.

Pioneering Automated GUI Interaction with Native Agents

An AI agent from ByteDance that looks at a computer or phone screen and performs tasks by clicking, typing, and navigating, you give it a goal in plain English and it works out the steps itself, on desktop, mobile, and web browsers.

A blazingly fast JSON serializing & deserializing library

A Go JSON library from ByteDance that encodes and decodes JSON several times faster than the standard library, using JIT compilation and SIMD CPU instructions, a near-drop-in replacement for encoding/json.

A Lightweight Recommendation System

ByteDance's open-source deep learning framework for building large-scale recommendation systems, the same kind of engine that powers TikTok's video feed, with built-in support for real-time model updates.

A HTML5 video player with a parser that saves traffic

A browser video player from ByteDance that streams MP4 files in segments to reduce buffering, and supports HLS, DASH, and FLV formats through a fully plugin-based architecture.

🍎Transform an SVG icon into multiple themes, and generate React icons，Vue icons，svg icons

A library of 2,000+ icons by ByteDance that supports four visual styles, outline, filled, two-tone, and multi-color, and ships as ready-to-use components for React, Vue, and plain SVG.

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Dolphin is an AI model that reads photos or scans of documents and converts them into structured text, tables, formulas, and code, handling 21 types of document elements with JSON or Markdown output.

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.

A TypeScript framework from ByteDance for building your own drag-and-drop visual workflow editors in the browser, with built-in node types for AI calls, HTTP requests, loops, and conditional logic.

No description.

Taming Stable Diffusion for Lip Sync!

A high performance and generic framework for distributed DNN training

LightSeq: A High Performance Library for Sequence Processing and Generation

ByteX is a bytecode plugin platform based on Android Gradle Transform API and ASM. 字节码插件开发平台

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

Elkeid is an open source solution that can meet the security requirements of various workloads such as hosts, containers and K8s, and serverless. It is derived from ByteDance's internal best practices.

:fire: ByteHook is an Android PLT hook library which supports armeabi-v7a, arm64-v8a, x86 and x86_64.

🔥🔥 btrace (AKA RheaTrace) is a high-performance Android & iOS tracing tool built on Perfetto. It not only times your methods but also reveals why they’re slow.

Android Single Activity Framework compatible with Fragment.

AlphaPlayer is a video animation engine.

:fire: ShadowHook is an Android inlinehook library which supports thumb, arm32 and arm64.

UME is an in-app debug kits platform for Flutter. Produced by Flutter Infra team of ByteDance

A RocksDB compatible KV storage engine with better performance

No description.

Universal Utilities for Go

No description.

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

No description.

Appshark is a static taint analysis platform to scan vulnerabilities in an Android app.

An interesting go struct tag expression syntax for field validation, etc.

BitSail is a distributed high-performance data integration engine which supports batch, streaming and incremental scenarios. BitSail is widely used to synchronize hundreds of trillions of data every day.

[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization

Official Repo For Pixel-LLM Codebase: Sa2VA (Arxiv-25), SAMTok (CVPR-26), VRT, SaSaSa2VA (1-st solution for LSVOS)

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholarly queries.

SALMONN family: A suite of advanced multi-modal LLMs

The tool of obfuscated aab resources.(Android app bundle资源混淆工具)

No description.

[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

A fast communication-overlapping library for tensor/expert parallelism on GPUs.

[CVPR 2026] 🔥🔥 Official Repo of USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

No description.

Fastbot(2.0) is a model-based testing tool for modeling GUI transitions to discover app stability problems

This repo contains the code for 1D tokenizer and generator

sensitive information protection toolkit

No description.

Multi-view Diffusion for 3D Generation

A fast JSON serializing & deserializing library, accelerated by SIMD.

A multi-party collaborative machine learning framework

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

A simple and easy-to-use Go mocking library derived from ByteDance's internal best practices

Enterprise-oriented Generic Proxy Solutions

The code releasing for https://image-dream.github.io/

iBOT :robot:: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

[AAAI 2025] Official codes of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".

No description.

a set of tools for measuring and debugging performance of frontend applications

No description.

A highly customizable streaming flow builder.

A new feature guide component by react 🧭

[ECCV 2026] DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

The official repo for "Vidi: Large Multimodal Models for Video Understanding and Editing"

ComfyUI Lumi Batcher is a batch processing extension plugin designed for ComfyUI, aiming to improve workflow debugging efficiency. Traditional debugging methods require adjusting parameters one by one, while this tool significantly enhances work efficiency through batch processing capabilities.

[NeurIPS 2025] Official implementation of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation".

HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling

[CVPR2024] SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System

About Fastbot(2.0) is a model-based testing tool for modeling GUI transitions to discover app stability problems

Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

[CVPR 2025 Highlight🌟] Official ComfyUI implementation of "HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis"

vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and network proxy technologies to enforce access control from system calls to application protocols — protecting workloads including AI Agents.

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

A high performance and lightweight rule engine written by Golang.

A model compilation solution for various hardware

[ICLR 2026] Official repo for paper "Video-As-Prompt: Unified Semantic Control for Video Generation"

KV cache store for distributed LLM inference

🔥gg is a basic library of generics for Go language developed by ByteDance. It is based on the Go 1.18+ generic features and provides efficient, type-safe and rich generic data structures and tool functions.

Syllepsis is an out-of-the-box rich text editor.

No description.

[HPCA 2026] AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and versatility of software and hardware.

Awesome samples for Volcengine AgentKit Platform with VeADK.

Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944

No description.

[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

The Family of Diffusion Protein Language Models (DPLM)

Lynx: Towards High-Fidelity Personalized Video Generation

[ICLR 2026] Official Repo For "BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration"

Online Multi-Granularity Distillation for GAN Compression (ICCV2021)

Reproduction code of paper "World Model-based Perception for Visual Legged Locomotion"

No description.

Font files available from ByteDance Fonts

Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

Q-Insight Family: Q-Insight, VQ-Insight and RALI (NeurIPS 2025 Spotlight, AAAI 2026 Oral, and ICLR 2026 Oral)

Interrupts-off or softirqs-off latency tracer

🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX

Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.

Web-Bench is a benchmark designed to evaluate the performance of LLMs in actual Web development.

[CVPR 2024] Official implementation of "DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations"

Cloud Shuffle Service(CSS) is a general purpose remote shuffle solution for compute engines, including Spark/Flink/MapReduce.

An acceleration library that supports arbitrary bit-width combinatorial quantization operations

Vue component for xgplayer, a HTML5 video player with a parser that saves traffic

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

Official repository of PXDesign

No description.

PatchEval: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities

No description.

a text-conditional diffusion probabilistic model capable of generating high fidelity audio.

video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates high-quality audio-visual video captions, which is developed by the Department of Electronic Engineering at Tsinghua University and ByteDance.

DanmakuRenderEngine is a lightweight and scalable Android danmaku library. 轻量级高扩展安卓弹幕渲染引擎

No description.

[CVPR 2026] 🔥🔥 Official Repo of UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

Repo2Run is an LLM-based agent that automates environment configuration by generating error-free Dockerfiles for Python repositories.

ParaGen is a PyTorch deep learning framework for parallel sequence generation.

A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.

Large batch training of CTR models based on DeepCTR with CowClip.

[ICCV 2025] Code & Data for: SuperEdit - Rectifying and Facilitating Supervision for Instruction-Based Image Editing

No description.

BAMBOO (Bytedance AI Molecular BOOster) is an AI-driven machine learning force field designed for precise and efficient electrolyte simulations.

No description.

Libtpa(Transport Protocol Acceleration), a DPDK based userspace TCP stack implementation.

A CLI tool to help with diagnosing Node.js processes basing on inspector.

[AAAI2025] DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder

A Unified Evaluation Suite for Protein Design

An accurate and trainable end-to-end protein-ligand docking framework

An interprocess message bus system built in Rust.

[ECCV 2026] Generative Refinement Networks for Visual Synthesis (Support C2I & T2I & T2V)

ICLR 2025 paper X-NeMo & Project X-Portrati2

No description.

DCFrame is a Swift UI collection framework, which can easily create complex UI.

🔥 [ICCV 2025 Highlight] Official open-source repo for LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition

JAX accelerated Quantum Monte Carlo

CausalMatch is a Bytedance research project aimed at integrating cutting-edge machine learning and econometrics methods to bring about automation in decision-making process.

Optimized JDK with high compatibility and performance

A faster experimental wasm-based tar implementation for browsers.

No description.

This repo contains the code for our paper Towards Open-Ended Visual Recognition with Large Language Model

Structural Quality Assessment for Biomolecular Structure Prediction Models

Official implementation of "Flow Based Policy for Online Reinforcement Learning"

No description.

Official implementation of GR-MG

A lightweight parameter server interface

[CVPR 2025] StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer

No description.

Official Implemetation of ConfDiff (ICML'24) - Protein Conformation Generation via Force-Guided SE(3) Diffusion Models

byteff source code

Official implementation of CVPR 2025 paper "ID-Patch: Robust ID Association for Group Photo Personalization". This work proposed propose ID-Patch, a fast and robust method that links identity features to 2D positions via visual patches and embeddings.

code repository for Practical Deep Dispersed Watermarking with Synchronization

Codes for our paper "Programming Biomolecular Interactions with All-Atom Generative Model"

NxtUnit is an automatically unit test generation application for Go.

The official repo for “WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?“

Efficient and Accurate Neural-Network Ansatz for Quantum Monte Carlo

The official implementation of DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design (ICML 2023)

[ICLR2023] Official Implementation of Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning (https://arxiv.org/abs/2210.00226)

Unix dgram, seqpacket, etc binding for Node.js.

The official repo for "Where do Large Vision-Language Models Look at when Answering Questions?"

A free and open-source workload scheduler which supports diverse high-performance computing and analytical applications.

Flutter pull_to_refresh widget

No description.

No description.

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering. A comprehensive evaluation of multimodal large model multilingual text perception and comprehension capabilities across nine widely-used yet low-resource languages.

No description.

No description.

A library combining solid quantum Monte Carlo and neural network.

No description.

vArmor-ebpf is a specialized project dedicated to maintaining the BPF code utilized by vArmor.

BytevalKit-Emb is a modular embedding model evaluation framework that implements automated model performance assessment through standardized processes. The framework adopts a configuration-driven design and supports multiple task types and model architectures.

No description.

The official code for "GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning"

No description.

F-16 is a powerful video large language model (LLM) that perceives high-frame-rate videos, which is developed by the Department of Electronic Engineering at Tsinghua University and ByteDance.

Import data from clickhouse to hadoop with pure SQL

No description.

No description.

batchRun is an ansible-similar IT automation system, which is more suitable for IC industry.

A demo for DouyinOpenPlatform, include iOS and android.

Learning Harmonic Molecular Representations on Riemannian Manifold, ICLR, 2023

No description.

No description.

This is a mirror repository of gpu4pyscf. Please refer to https://github.com/pyscf/gpu4pyscf for the latest development.

libDMET with quantum computing chemistry solvers of UCCSD

An implementation combining FermiNet with effective core potential (ecp). For paper, see https://arxiv.org/abs/2108.11661.

No description.

FLAC

SIFThinker: Spatially-Aware Image Focus for Visual Reasoning

No description.

No description.

APIs to help Rust programs use Spire workload API

No description.

This repo contains the implementation of container scheduling algorithm, aiming at maximizing service affinity.

No description.

No description.

Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking (ICLR 2026)

Findings of ACL'25 DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models

No description.

No description.

No description.

The official repository for "CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation" published in ICML 2026.

No description.

No description.

The systemd System and Service Manager