NVTabular
NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.
HYSEN LABS 项目目录
用精准分类、人工校验元数据和实用语境,系统整理值得关注的开源项目。
NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.
a self-hosted webui for 30+ generative ai
The Cloud Sandbox Built for AI Agents
Self-hosted software for managing artisanal D2C micro-businesses
Training library for local feature detection and matching
Open-source AI reverse-engineering agent platform and MCP server for Ghidra, Frida, x64dbg and Rizin — automated PE/APK/binary analysis, CTF and malware research, with 100+ MCP tools and a 194-article runnable knowledge base.
Dynamic MBTI Personality Simulation for LLM Agents via Carl Jung's Theory. A framework that enables LLM agents' MBTI personalities to naturally evolve and grow through interaction.
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
Turn meetings into live agent loops. Record, transcribe, and analyze meetings with real-time AI intelligence — before, during, and after calls.
Lakehouse native graph engine with git-style workflows
Self-improving AI testing engine across Android, iOS, and Web.
eBPF-based Linux kernel observability 🚀🚀
80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.
DataInfra Series. Redact EVERYTHING with local llms and vlms.
Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
高效的多媒体支持操作库,可简单配置操作相册、拍照、录音、录音等多种功能。还支持配套使用显示图片、视频、音频的九格功能。 。
[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.
讨厌延迟的模拟器:Acorn Electron、BBC Micro 和 Archimedes、Amstrad CPC、Apple II/II+/IIe 和早期 Macintosh、Atari 2600 和 ST、ColecoVision、Enterprise 64/128、Commodore Vic-20 和 Amiga、MSX 1/2、Oric 1/Atmos、早期 PC 兼容机、Sega Master System、Sinclair ZX80/81 和ZX Spectrum、Tandy CoCo 和 Thomson MO5/6。
🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free.