Havuz

DSH 打游戏插件合集：游戏感知 / 视觉实体 / 游戏学习（规则+流程+闸门+知识库）/ 直播桥 / 启动器，5 个可安装 bundle 一键安装

A desktop-native Windows system tray Telegram bot that monitors AniList for new anime announcements and releases with network auto-recovery,

Record a sky camera around the clock, keep the footage on your own disk, and find what flew past.

A laser dry-fire shooting game: your matte monitor is the target, an ordinary webcam watches it from the side, and your laser trainer leaves

An AI that plays Pokémon FireRed on a real Nintendo Switch: capture card in, emulated Bluetooth controller out. LLM strategist + determinist

Your real-life buddy duck: an open-source embodied AI robot duck that walks, hears, sees, and has a life of its own. 让 DuckBuddy 成为你真正的生活伙伴鸭

Runs Hugging Face ONNX models on any Nx backend, with no per-architecture code

I gave Claude Code 120 pages of my handwritten college notes. It gave me back my handwriting as a real font, in 66 minutes for $13.68.

Finds a stolen bike on second-hand marketplaces by ranking photos, not keywords — a CLIP pre-gate in front of a vision-LLM recognition pass.

3DGS 在线重建查看器 + 个人主页（郑州大学双足实验室 3D 方向考核作品）

Turn your cameras into Home Assistant sensors with a local AI: garage door open/closed, people and cars, water, gas and power meters read by

冒险岛怀旧服（国服）自动练级工具 · 基于计算机视觉，免安装包解压即用（普通用户请看 README_用户版）

🎬 Autonomous AI Studio for Manhwa & Webtoon Recaps — Vision Pipeline (YOLOv8 + Magi v2), Multi-Voice TTS & Video Synthesis

Scaler 2 Music Theory Tool 2026: Direct DAW Integration for Windows 10 and 11

Best AI QA Evidence Recorder MCP Server for Automated Testing 2026

AI Form Coach for Perfect Workout Technique 2026

geo-sleuth, fotoğraftaki çevresel ipuçlarını analiz edip konum tahmini ve kanıt görselleri üreten bir agent skill’idir.

Neden yükseliyor · Dokuz günlük bir repoda 453 yıldız dikkat çekici; fotoğraftan konum bulma demosu ve birden fazla agent ortamında kullanılabilmesi ilgi çekmiş olabilir. Ancak son 28 günde 10 commit ve tek farklı yazar, benimsemenin veya sürdürülebilir geliştirmenin henüz güçlü kanıtı değil.

High-performance neural networks engine for web, built on top of TypeGPU

ASEpochs 的多模态课堂观察 AI Agent：摄像头实时感知、行为推理、异常语音提醒与课堂报告

[arXiv 2026] Code for "Elastic Token Compression for Pixel-Space Diffusion Transformers"

Open-core ADAS drift scoring and a free local dashcam mount-health agent (Pulse). Shadow mode. Apache-2.0.

一款把任意图片转换为专业生图提示词的 Chrome / Edge 浏览器插件。支持网页右键识图、本地上传与剪贴板粘贴，生成中文、英文和 JSON 提示词，并提供历史记录与收藏。

Free, open-source AI clip generator and Opus Clip alternative. Turns podcasts, vlogs, tutorials and stream VODs into captioned YouTube Short

Browser-based procedural machine-vision graphics for local video.

Computer vision AI training in any GPU

AI Form Checker 2026: Perfect Your Squat, Deadlift & Bench Press Form

Unbagrnd - Free, Fast & Open-source AI-powered background remover for Windows, macOS, Linux and Android.

Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.

An optimized handwritten digit recognition model delivering exceptional accuracy, high-speed performance, and compatibility with low-end har

DSH Vision Toolkit, DeepSeek Harness içindeki text-only agent'lara görsel görevler için araçlar ve yerel entegrasyon sunan bir plugin'dir.

Neden yükseliyor · 45 günlük yaşına karşılık 883 yıldız ve son 28 günde 49 commit dikkat çekici; README de kolay kurulum ve doğrudan görsel kullanımı vurguluyor. Ancak bu yükselişin nedenini veya gerçek kullanım yaygınlığını verilen verilerle doğrulamak mümkün değil; 49 commit'in yalnızca 2 farklı yazardan gelmesi geliştirme faaliyetinin yoğun ama dar bir ekibe bağlı olduğunu gösteriyor.

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery

Image → ASCII art by direct optimization. Any monospace font, optional color.

Self-hosted AI video analysis: summaries, chapters, keyframes, transcripts and SRT / JSON export. AI 视频总结、字幕提取与结构化分析。

Autopilot for your Clash of Clans base on Google Play Games on PC — farming, wall upgrades, and auto base progression. PySide6 UI, OpenCV te

AI-powered real-time object detection, tracking, and video intelligence platform using YOLO and computer vision.

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protoco

Globally accessible autonomous robot featuring AI object tracking, 4G remote control, edge computing, WebRTC streaming, and environmental se

EasyOCR's accuracy in a single Rust binary: CRAFT text detection and gen2 CRNN recognition over ONNX, with no Python runtime.

Calibrated flatbed scans to editable, validated FreeCAD sketches.

Give Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before pow

Turn a phone flip-through video, photos, or a PDF of a book into a clean, proofread EPUB/PDF/Markdown — local vision-LLM digitization with a

A gesture-based computer control project that enables users to interact with a PC using hand movements and gestures. This project combines c

An interactive web-based Iron Man Arc Reactor experience. Uses real-time hand tracking via webcam and animated canvas rendering to create a

餐饮连锁数字化 + AI 全景蓝图:原串(平价烤串连锁)的架构决策、业务口径、踩坑实录与可直接喂给 AI 的复刻指令。纯自然语言方案,不含代码与任何真实经营数据。

AI/ML Engineer in progress — LLM, RAG, Computer Vision. Open to full-time AI Engineer roles.

Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores

ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to pre

Flatbed-scanner photometric stereo for generating normal, albedo, height, and alpha texture maps.

Local-first cinematic still archive for filmmakers. Search your frames by look, mood, technique or director with SigLIP semantic search; ing