🖨️ Automated scanner document processor with AI-powered naming and WebDav integration. Receives scans via FTP, extracts text using Vision AI, generates intelligent filenames with Ollama AI, and uploads to your cloud storage.
Open-source flipbook.page clone — every page is an AI-generated illustration, click anywhere to explore deeper. Next.js + FastAPI + Modal. BYO keys.
The self-hosted AI workstation. Autonomous screen agents, 3-tier neural routing, parallel agent swarms, video generation, 4K/8K upscaling, RAG, voice interface, 70+ tool execution engine — all running locally on your hardware.
Self-hosted AI photo intelligence tool. Uses local vision models via Ollama to describe, tag, rename, and search your photos. No cloud needed.
AI-powered browser automation agent using a dual-LLM architecture. The orchestrator (qwen3-vl-32k) creates execution plans from screenshots, while the executor (llama3.1:8b) translates steps into browser actions using an accessibility tree for reliable element selection. Local, private, powered by Ollama.
evMLP: An Efficient Event-Driven MLP Architecture for Vision
Локальная мульти-агентная система на self-hosted LLM (Ollama). 3 канала (Telegram/консоль/MAX), 4 типа моделей (LLM/embed/vision/voice), мультимодальность (текст/PDF/фото/голос), роли Planner/Executor/Critic с рефлексией. Инструменты: почта, Яндекс.Диск, web, OCR, cron-планировщик. Семантическая память (sqlite-vec). Coverage 88%. Без облачных API.
AI video editing skill that watches your footage before cutting. Vision model analyzes every frame, scores usability, drops bad takes, reorders by narrative, then renders with ffmpeg. For Claude Code, Cola, OpenClaw. 会看画面的 AI 自动剪辑 Skill——先用视觉模型看懂素材再决定剪哪几秒。
This is a fork of SpaceInvaderOne's repo to fix some issues I had with the software until he pulls the changes or fixes them himself. It also allows for integration to my gallery app Eyeris. github.com/vonhex/eyeris
基于视觉大模型的前端(React+Antd)全自动 CRUD 代码生成器 🚀 / AI-powered full-automatic CRUD code generator.
AI 桌面直播弹幕姬 — 让 AI 一边看你的屏幕一边像直播观众一样发弹幕吐槽
Compress images before AI vision analysis — save ~80% token costs. Works with Claude Code, Cursor, Codex, and any AI coding agent.
Next-gen AI Optical Music Recognition (OMR) platform. Convert sheet music images into playable ABC notation instantly using Google Gemini 3 Pro Vision. Built with React 19, TypeScript, and Tailwind.
Find a TikTok user's slideshow posts and OCR the caption text off every slide with an AI vision model.
lookdev-auto — a Claude Code skill for automated visual tuning: a vision model rates rendered variants in a loop.
Fast, resumable batch image captioning for local vision models (LM Studio, Ollama, any OpenAI-compatible) — CLI + FastAPI web studio, multi-format output
AI Gateway with visual fallback routing, hybrid multi-backend search, and protocol translation for Claude Code & Codex
🔍 A CLIP-powered image similarity finder built with Streamlit — upload a query image and find the most visually similar matches from a gallery using deep visual embeddings.
Add a description, image, and links to the vision-model topic page so that developers can more easily learn about it.
To associate your repository with the vision-model topic, visit your repo's landing page and select "manage topics."