你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

Embedded web server, with TCP/IP network stack, MQTT and Websocket

Detect and correct audio-video synchronization offsets in media files — automatically or manually.

Fast and accurate automatic speech recognition (ASR) for edge devices

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

MimiClaw: Run OpenClaw on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS.

Windows Application Driver

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Run Windows apps on 🐧 Linux with ✨ seamless integration

Visual Causal Flow

base on ncnn_llm build a ragsystem

ncnn implementation of Z-Image image generater

基于 ncnn 的 Stable Diffusion 推理小工具，用于给 ncnn-llm 适配“图片生成”能力（作为 MCP 工具/后端可执行程序被调用）。

[ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting

Open-Source Frontier Voice AI

High-efficiency floating-point neural network inference operators for mobile, server, and Web

Go/React开发的端到端webrtc的文件传输/文字传输/桌面共享，安全，隐私，数据不经过服务器。

A repo for llm on ncnn

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

Using ncnn to test the reasoning performance of neural network

Contexts Optical Compression

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

This is the official implementation of our paper: "MiniMax-Remover: Taming Bad Noise Helps Video Object Removal"

molly, an LLM designed to understand multi-omics data.

The fastest and highest-quality deep learning powered Sora2 watermark cleaner.

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation