Google is upgrading the Chrome browser into an intelligent productivity tool. In the latest test version, the new tab search box now includes a full-featured "+" menu, supporting image uploads, becoming an integrated control center and enhancing the browsing experience.
Google Search has added a "+" button that supports uploading images or documents for in-depth analysis using the Gemini AI model. This feature is currently in an experimental phase and available to only a select group of users. After uploading, Gemini can parse the content, allowing users to ask questions instantly and get contextually relevant answers, such as asking where to purchase parts after uploading a manual.
Google tests merging 'AI Overview' and 'AI Mode' on mobile, enabling multi-turn conversations directly on search results without page jumps. It supports text, voice, and image inputs, with conversations up to three times longer than traditional searches, while retaining source citations and web rankings. The VP of Product states the redesign aims to eliminate user choice costs between search and chat, facilitating continuous queries and instant r....
AWS unveils four self-developed 'Nova2' AI models at re:Invent 2025, covering text, image, video, and speech with built-in web search and code execution, claiming leading price-performance. Nova2 Lite offers cost-effective inference, outperforming Claude Haiku4.5 and GPT-5Mini at about half the cost, while Nova2 Pro targets complex agent tasks.....
Aladin AI is a browser-based AI that offers a variety of tools and features.
A virtual computer assistant that can perform tasks such as searching or creating images.
Quickly get the true value of items through photography.
Reverse image search and face recognition search engine
Google
$0.49
Input tokens/M
$2.1
Output tokens/M
1k
Context Length
Openai
$2.8
$11.2
Xai
$1.4
$3.5
2k
Anthropic
$105
$525
200
$0.7
$17.5
Alibaba
-
$1
$10
256
$3.9
$15.2
64
Bytedance
$0.8
$2
128
Qdrant
This is an ONNX ported version of the Microsoft ResNet - 50 model, designed for efficient image classification and similarity search, providing optimized inference performance.
ONNX ported version based on CLIP ViT-B/32 architecture, suitable for image classification and similarity search tasks.
google
OWL-ViT is a zero-shot text-conditioned object detection model that can search for objects in images via text queries without requiring category-specific training data.
facebook
RegNet image classification model trained on ImageNet-1k, featuring an efficient network structure designed via neural architecture search
RegNet model trained on the ImageNet-1k dataset, an efficient vision model designed through neural architecture search
RegNet image classification model trained on ImageNet-1k, designed using neural architecture search technology
RegNet model trained on ImageNet-1k, an efficient vision model designed through neural architecture search
RegNet image classification model trained on ImageNet-1k, featuring an efficient network structure designed through neural architecture search
RegNet is an image classification model designed through neural architecture search, trained on the ImageNet-1k dataset.
RegNet is a vision classification model trained on ImageNet-1k, featuring an efficient network structure designed through Neural Architecture Search (NAS)
RegNet image classification model trained on the ImageNet-1k dataset, designed using neural architecture search technology
RegNet model trained on ImageNet-1k, an efficient vision model designed via neural architecture search
RegNet is a vision classification model trained on ImageNet-1k, featuring an efficient network structure designed through neural architecture search
RegNet model trained on imagenet-1k, an efficient vision model designed via neural architecture search
RegNet image classification model trained on the ImageNet-1k dataset, featuring an efficient network structure designed via neural architecture search
Unsplash Image Search Integration Server
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
This is an MCP server project for Google Calendar, providing integration functions with Google Calendar. It allows reading, creating, updating, and searching for calendar events through standardized interfaces. It supports functions such as adding events from images, calendar analysis, attendance status check, and automatic event coordination.
An implementation of a local proxy server and client based on the MCP platform, integrating multiple AI tool functions such as weather query, Google search, camera control, image generation, and intelligent dialogue, supporting modular expansion and high-performance concurrent processing.
An MCP server implementation integrating the Brave Search API, providing web search, local point of interest search, video search, image search, and news search functions.
An MCP server for interacting with the digital collection of the Louvre Museum, providing functions for artwork search, detail viewing, and image acquisition.
An MCP server based on TypeScript that provides Gyazo image integration services, supporting image search, retrieval, upload, and metadata access functions.
The Oxenstierna project aims to provide functions for searching, obtaining, and analyzing archive content by integrating multiple APIs (such as OAIPMH, IIIF, and Search API) of the Swedish National Archives, including the HTR (Handwritten Text Recognition) process and image processing.
Deep Research is an agent - based tool that provides web search and advanced research functions, supports PDF analysis, image description, and YouTube transcription extraction, and can run as an MCP server.
An MCP server and command-line tool for searching and browsing transcriptions of historical documents from the Swedish National Archives, supporting full-text search, page transcriptions, document browsing, and high-resolution image access.
The Model Context Protocol (MCP) is an open - source protocol that provides a series of reference implementations and community - developed servers. It aims to provide large language models (LLMs) with secure and controllable access to tools and data sources. These servers demonstrate the diversity and scalability of MCP, covering various functions from file system operations to database integration, from web search to AI image generation.
The Rijksmuseum MCP Server provides access to museum art collections through natural language interaction, supporting search, analysis, and image viewing functions.
The remote MCP server provided by Jina AI offers functions such as web content extraction, web search, academic search, image search, query expansion, document re - sorting, and deduplication through the Reader, Embeddings, and Reranker APIs.
An MCP server based on TypeScript that provides access to the Pixabay image search API
A customized MCP server by MiniMax for Coding Plan users, providing AI-driven web search and image analysis tools, optimized specifically for the code development workflow, and can be integrated into MCP clients such as Claude Desktop and Cursor to enhance the programming experience.
Archive Agent is an intelligent file indexing tool that supports searching and querying file content through natural language. It combines AI search (RAG engine), automatic OCR, and the MCP interface, and can handle various file types, including text, documents, PDFs, and images.
This project implements an MCP server based on the Unsplash API, providing tools for searching and downloading images, supporting multiple resolutions and search conditions.
The Maccy Clipboard MCP Server is a service tool that exposes Maccy's clipboard history to AI assistants such as Claude. It supports searching, viewing, and managing clipboard content, including image support and data statistics functions. However, be aware of the risk of sensitive data leakage.
The MCP Gemini API server is a Google Gemini API proxy service designed for Cursor and Claude, providing functions such as text generation, image analysis, video analysis, and web search.
An MCP service for Unsplash image search and retrieval implemented in Go, providing functions such as keyword search, random image retrieval, and detailed image information query, supporting multiple connection modes and rich filtering options.