Find trending repositories by name or description.
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.
A HTML5 video player with a parser that saves traffic
A multi-party collaborative machine learning framework
A RocksDB compatible KV storage engine with better performance
A blazingly fast JSON serializing & deserializing library
A highly customizable streaming flow builder.
Rust async runtime based on io-uring.
A simple and easy-to-use Go mocking library derived from ByteDance's internal best practices
A fast JSON serializing & deserializing library, accelerated by SIMD.
Enterprise-oriented Generic Proxy Solutions. Maintenance mode now, please switch to use [VEY](https://github.com/VEY-OSS/vey) for new development efforts
Python wrapper for ByteDance's Seedance 2.5 API — Text-to-Video, Image-to-Video, realistic human faces, native 4K, consistent character generation.
vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and NetworkProxy technologies to enforce access control from system calls to application protocols — protecting workloads including AI Agents.
Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
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.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Awesome samples for Volcengine AgentKit Platform with VeADK.
[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation
DeerFlow 源码解析 - ByteDance 开源 Super Agent Harness 深度解析
Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, reads draft_content.json and draft_info.json (剪映草稿) directly. Not affiliated with ByteDance.
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
The codebase of Cola DLM
Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
A from-scratch C++17/ggml port of Depth Anything 3 (ByteDance)
EdgeBench: Unveiling scaling laws of learning from real-world environments