HYSEN LABS DIRECTORY
Verified repositories, classifications and analysis from the bytedance organization.
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.
GitHub describes it as The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra. The repository metadata lists TypeScript as its primary language. The metadata lists the Apache-2.0 license. This article stays within the project description and details documented in the GitHub repository README.
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.
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.
A generic Android PLT hook library supporting 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.
A general-purpose Android inline hook library supporting Thumb, ARM32 and ARM64.
A RocksDB compatible KV storage engine with better performance
Toward High-Accuracy Open-Source Biomolecular Structure Prediction.
Universal Utilities for Go
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)
SALMONN family: A suite of advanced multi-modal LLMs
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.
A fast JSON serializing & deserializing library, accelerated by SIMD.