bytedance

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.

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

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

Pioneering Automated GUI Interaction with Native Agents

A blazingly fast JSON serializing & deserializing library

A HTML5 video player with a parser that saves traffic

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

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.

Taming Stable Diffusion for Lip Sync!

🔥 [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.

通用的Android PLT hook库，支持armeabi-v7a，arm64-v8a，x86，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.

通用的Android inline hook库，支持thumb，arm32，arm64

A RocksDB compatible KV storage engine with better performance

Universal Utilities for Go

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

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

Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), 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.

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

SALMONN family: A suite of advanced multi-modal LLMs

[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.

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

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

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

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

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

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

A multi-party collaborative machine learning framework

Enterprise-oriented Generic Proxy Solutions. Maintenance mode now, please switch to use [VEY](https://github.com/VEY-OSS/vey) for new development efforts

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

A highly customizable streaming flow builder.

[ECCV 2026 Oral] 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.

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

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

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.

Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"