foundation-models-utilities

Emerging and experimental patterns for building with the Foundation Models framework

Trend2Video-Pro

The open-source Trend-to-Video Agent Framework for content creators

viitor-voice-nar

ViiTorVoice-NAR ViiTorVoice 是一个面向语音克隆与语音局部编辑的非自回归语音生成系统。项目当前以 gRPC v2 拆分服务作为主要部署路径，并提供 HTTP 网关用于端到端调用。 核心能力包括： - 语音克隆：输入提示音频或提示音 codebook，生成指定文本对应的语音。 - 局部编辑：输入原始音频、原始文本和修改后文本，自动定位差异区域并重合成局部片段。 - 情感与副语言控制：支持在文本条件中插入情感标签和副语言信息，并通过 CFG 增强控制效果。 - 低延迟推理：支持 first block 推理模式，端到端首帧返回时间可以做到约 60ms。 模

visa-vulnerability-agentic-harness

Visa Vulnerability Agentic Harness

veltoc

Veltoc Model 01 is a ESP32 powered, retro-inspired environmental monitor with an E-Ink display. It can monitor temperature, humidity and air pressure. Connect to wifi to also display the current time.

remove-ai-flavor-writing-skill

去AI味 skill for Codex: a compact Chinese AI writing humanizer for AI味清理, template sentence shells, and fake engagement endings.

awesome-jepa

Curated resources for JEPA (Joint Embedding Predictive Architecture) world models and self-supervised learning

skills

Skills for coding agents

GreatXML

GreatXML bitlocker bypass vulnerability

enableMacosAI

国行 Mac 一键开启完整 Apple 智能(端侧 + Private Cloud Compute 云端)· macOS 27 / Apple Silicon

MicroRAG

MicroRAG A minimal Retrieval-Augmented Generation RAG system implemented from scratch in pure Python, without any external ML libraries. **纯Python从零实现的最小可运行RAG系统，无外部机器学习依赖。** --- 核心特性 / Core Features | 特性 / Feature | 说明 / Description | |----------------|-------------------| | **Retriever** | 基于

chubbyskills

chubby 自用知识库实用skill集合 - AI驱动的自动化工作流工具，可以帮助你从各个渠道获取信息，搭建自己的知识库