Havuz

An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active

Method-agnostic smart garden companion built with React Native, Expo, and TypeScript. Adapts to soil, hydro, container, or indoor setups wit

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence

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

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

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.

Native AI keying runtime and OFX plugin for DaVinci Resolve, built in collaboration with Corridor Digital.

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation wi

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

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co

Open-source video processing core and CLI. Search and annotate local videos with your own model endpoints.

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

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

A skill tool for Codex and Claude Code that converts images, PDFs, and image-based PPTX files into editable PowerPoint presentations.

Codex skill for converting raster logos into smooth minimal SVG plus standalone HTML previews.

免费、注重隐私的在线 AI 图像处理工具箱（包含一键抠图、去水印、老照片修复等）。无水印，免注册。| A free, privacy-first online AI image toolkit featuring one-click background removal, wat

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

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

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。

Real-time YOLOv8n UAV detection on the RK3588S NPU | saturates the sensor at 46 FPS | ~140 MB RAM | fully hardware-accelerated (ISP+RGA+NPU)

OSX launcher and GPU-accelerated CLI tool for AI agents. Open-source computer use tool.

Zero-token, on-device vision for AI agents — OCR, pixel-exact UI targeting, and face grouping on Apple Vision. Pure Swift, single binary, no

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

Open-source AI that watches and hears your screen and reacts live as any personality you design — for faceless content, autonomous AI stream

A local-first Python personal AI assistant for reasoning, memory, voice, vision, automation, and device control.

[ECCV 2026] WarpI2I: Image Warping for Image-to-Image Translation.

Building an Image-to-Video (I2V) Model from Scratch

Real-time gesture-to-flight-command pipeline using MediaPipe Hands, rule-based + ML recognition, FastAPI WebSocket backend, and a React/Type

No OTPs. No registers. No buddy punching. Just a selfie. ZepIris is Zepto's purpose-built face authentication platform - engineered for scal

Control OpenLayers, Google Maps, and Leaflet with hand gestures via webcam. Uses MediaPipe for real time hand tracking to pan, zoom, and nav

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。

On-device subject cutouts, image labels, and OCR for React Native. Apple Vision (iOS) · Google ML Kit (Android). Built with Nitro Modules.

State-of-the-art background removal API for images and video. BiRefNet on Modal GPUs, ~200ms per image. 26 endpoints: cutouts, masks, PSD ex

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

Self-hosted drop-in replacement for Face++ Compare API — powered by DeepFace/Facenet512

Open-source AI coding agent. Desktop app, bring your own model. Writes code, browses the web, verifies its work. Apache 2.0.

Browser-based Rubik's Cube solver — upload a flat-net image, get the step-by-step solution.

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

Monorepo of creative engineering builds: computer vision HCI, WebGL 3D experiments, autonomous AI agents, and browser bots.

Turn slide screenshots and generated images into editable PowerPoint decks with visual-layer splitting, OCR evidence, and QA.

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

Multimodal AI studio powered by Qwen3.6-35B-A3B. End-to-end web app exposing visual reasoning, image captioning, and document understanding

Give text based LLMs in Claude Code working eyes using a local Ollama vision model. Screen capture, clipboard reading, and image file analys

Draw faces in one continuous line, your own bio signature.

Official LFM-LLIE implementation—first-place winner of the NTIRE 2026 Low-Light Image Enhancement Challenge non-reference track.

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

Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, State-S