HYSEN LABS DIRECTORY

#Apache 2.0

License tag · curated repositories and deep analysis.

4,603 curated open-source projects
★ 982

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

Python80 forks7 min read
★ 982

Self-supervised learning for spatial perception

Python50 forks10 min read
★ 981

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

Jupyter Notebook168 forks7 min read
★ 979

🏸 AI Badminton Hawk-Eye System

Python275 forks8 min read
liliu-z

stashbase

★ 978

Turn your local files into a Wiki for your agents. Open-source and local-first.

TypeScript31 forks5 min read
dexmal

opendw

★ 976

An Open-Source World Model for Action-Conditioned Embodied Intelligence.

Python56 forks7 min read
agentverse-os

AgentVerse-OS

★ 974

Personal cloud OS for a developer and their AI agents on a single server. One-command install on Ubuntu, then everything in the browser: a windowed desktop, isolated workspaces with VS Code, Claude Code and Codex, a store of 944 self-hosted apps, backups and updates. Access only via Tailscale, nothing exposed to the internet. Rust core, Svelte UI.

Rust27 forks7 min read
★ 973

A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.

HTML108 forks5 min read
sparklyr

sparklyr

★ 972

R interface for Apache Spark

R311 forks6 min read
kessler

gemma-gem

★ 971

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

TypeScript104 forks8 min read
block

berd

★ 971

a desktop app for getting work done with any model

TypeScript127 forks7 min read
nv-tlabs

ardy

★ 968

Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).

Python117 forks8 min read
★ 968

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Python47 forks8 min read
safebucket

safebucket

★ 965

On-prem file sharing made simple, fast and safe.

Go42 forks5 min read
★ 965

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

Python304 forks6 min read
data-prep-kit

data-prep-kit

★ 965

Open source project for data preparation for GenAI applications

HTML255 forks6 min read
★ 965

Dante Cloud is a cloud-native microservices foundation supporting both blocking and reactive services in parallel, and an intelligent base for AI Agent development, designed around Domain-Driven Design (DDD) with a focus on high-quality code and low security risk. Highly modular, it covers IoT device authentication, China's MLPS Level 3 compliance, and SM-series digital envelope encryption for APIs, plus multi-tenancy support. Its original design lets one codebase switch flexibly between microservices and monolith architecture, powering enterprise-grade intelligent applications.

Java217 forks8 min read
smartcorelib

smartcore

★ 962

A comprehensive library for machine learning and numerical computing. Apply Machine Learning with Rust leveraging first principles.

Rust112 forks8 min read
cdxiaodong

cain-agent

★ 961

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK

Python212 forks7 min read
RizRiyz

luvus

★ 958

Mission control for your AI agents

Rust68 forks8 min read