#
vision-ai
Here are 76 public repositories matching this topic...
🐊 Snappy's unique approach unifies vision-language late interaction with structured OCR for region-level knowledge retrieval. Like the project? Drop a star! ⭐
python docker typescript computer-vision nextjs document-retrieval rag fastapi vector-search document-understanding pdf-search vector-database vision-ai qdrant colpali multimodal-ai multivector-search deepseek-ocr visual-retrieval
-
Updated
Feb 9, 2026 - Python
📺 Instill Console for 🔮 Instill Core: https://github.com/instill-ai/instill-core
console ui computer-vision deep-learning frontend image-classification object-detection structured-data data-pipeline no-code model-serving vdp unstructured-data data-connector vision-ai versatile-data-pipeline
-
Updated
Mar 1, 2026 - TypeScript
Gemini Vision & Image Generation MCP for Claude Desktop and Claude Code
ai mcp gemini image-generation claude multimodal google-ai vision-ai claude-desktop model-context-protocol
-
Updated
Mar 3, 2026 - JavaScript
AI-powered video understanding — extract key frames from YouTube, Bilibili & any video page, get structured summaries via vision AI. Supports yt-dlp, Playwright, cloud browsers. AI驱动的视频理解-从YouTube， Bilibili和任何视频页面提取关键帧，通过VLM获得结构化摘要。支持yt-dlp、Playwright和一些常见云浏览器。
agent automation youtube video ai ffmpeg skills web-scraping bilibili vlm playwright yt-dlp ai-tools vision-ai openclaw
-
Updated
Mar 9, 2026 - JavaScript
[CVPRW'25] Official Code For "SK-RD4AD: Skip-Connected Reverse Distillation for One-Class Anomaly Detection"
computer-vision anomaly-detection industrial-ai one-class-classification vision-ai skip-connection cvpr-workshop-2025
-
Updated
Jul 7, 2025 - Python
This repository demonstrates YOLOv8-based license plate recognition with GCP Vision AI integration, enabling versatile real-world applications like vehicle identification, traffic monitoring, and geospatial analysis while capturing vital media metadata for enhanced insights.
python opencv machine-learning ocr computer-vision deep-learning gcp ml pytorch object-detection optical-character-recognition traffic-monitoring data-augmentation geospatial-analysis license-plate-recognition vehicle-identification media-metadata ultralytics vision-ai yolov8
-
Updated
Feb 1, 2024 - Jupyter Notebook
🌀 The world's first emotionally intelligent CLI that thinks, creates, and empathizes with developers. Autonomous AI with Vision, Dream Engine, and Emotional Intelligence.
-
Updated
Aug 15, 2025 - TypeScript
Bidirectional Markdown↔PDF converter with AI-powered vision. MD→PDF with beautiful themes, PDF→MD with LLaVA - open source & privacy-first
nodejs markdown cli open-source pdf converter documentation typescript ai bidirectional beginner-friendly hacktoberfest markdown-to-pdf puppeteer good-first-issue privacy-first vision-ai llava ollama pdf-to-markdown
-
Updated
Nov 5, 2025 - TypeScript
MDDenseResNet : Enhanced Malware Detection Using DNNs
deep-neural-networks deep-learning-algorithms malware-analysis cyber-security malware-detection-framework vision-ai
-
Updated
Jul 27, 2025 - Jupyter Notebook
MCQ_Grading_Bot is an AI-powered tool that grades solved MCQ exam sheets from images using Gemini Vision. It extracts student info, checks answers, calculates score, and displays detailed results—all through a simple Gradio interface in Colab.
python machine-learning ocr image-processing pillow edtech gradio educational-technology ai-project ai-in-education vision-ai google-generative-ai grading-bot automated-grading mcq-grading exam-evaluation exam-checking mcq-checker answer-sheet-evaluation
-
Updated
Jun 19, 2025 - Jupyter Notebook
AI-powered health platform with multi-LLM engine (GPT-4o, Claude, Gemini). Workout generation, medication tracking with OCR, vision AI, gamification with leaderboards/rewards. Self-hosted, privacy-first.
react nodejs docker express typescript ocr mongodb self-hosted gemini gamification openai fitness-tracker health-analytics tailwindcss privacy-first workout-generator vision-ai llm anthropic medication-tracking
-
Updated
Feb 15, 2026 - TypeScript
AI-Powered Kahoot Auto-Answer Chrome Extension — supports every question type
react javascript chrome-extension ai websocket dom-manipulation openai free quiz gpt kahoot kahoot-bot kahoot-hack kahoot-hacks kahoot-answers auto-answer vision-ai gpt-5
-
Updated
Mar 9, 2026 - JavaScript
Hybrid AI orchestration stack combining local LLMs (Ollama), vector search (Qdrant), and Azure AI Foundry for scalable RAG, Agentic AI, and Vision. Built with .NET 8 and Python.
python dotnet routing inference orchestrator open-ai rag vision-ai qdrant hybrid-ai ollama qwen mistral-7b agentic-ai azure-ai-foundry phi3-mini
-
Updated
Oct 12, 2025 - Python
General vision AI defect detection engine for MLops process/simulations
python opencv detection pytorch classification segmentation shell-scripting defect-detection mlops vision-ai
-
Updated
Mar 5, 2025 - Python
Vision Agent Analyst is a professional web application for automatic analysis of visual data (diagrams, interfaces, documents) using multimodal artificial intelligence models.
react python typescript computer-vision data-visualization image-analysis financial-analysis document-analysis ai-agents ui-review fastapi pdf-processing vision-ai llm multimodal-ai
-
Updated
Dec 8, 2025 - Python
Backend проекта Pinterest команды OND team
docker redis golang microservices kafka backend ci cd docker-compose metrics websocket grafana postgresql swagger prometheus clean-architecture grpc-go easyjson vision-ai pgxpool
-
Updated
Mar 2, 2024 - Go
Improve this page
Add a description, image, and links to the vision-ai topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the vision-ai topic, visit your repo's landing page and select "manage topics."