Google adds an AI feature to the Chrome browser, introducing the 'Nano Banana' image generation tool and the 'Deep Search' topic research feature in the latest beta version. Users can create images or perform information retrieval directly in the search box without switching pages to quickly start tasks.
Alibaba Cloud's Tongyi Lab open-sources Tongyi DeepResearch, a lightweight AI agent matching OpenAI's performance in information retrieval and reasoning, with 30B active parameters.....
Tongyi Lab of Alibaba released the open-source tool WebShaper, adopting an innovative formal-driven information retrieval paradigm. It achieved a score of 60.19 on the GAIA benchmark, surpassing Claude 3.5 Sonnet and GPT-4o. The framework ensures consistency between knowledge structure and reasoning logic through structured data generation methods, significantly enhancing AI's ability to handle complex tasks. As the fourth tool in the WebAgent series, WebShaper has received over 4,000 stars on GitHub and is driving the development of the open-source AI community.
Alibaba's WebSailor, an open-source AI agent framework, excels in BrowseComp-en/zh and SimpleQA tests. Features knowledge graph-based task generation and reinforcement learning with RFT/DUPO. Introduces data obfuscation for enhanced AI training.....
An online encyclopedia that provides extensive knowledge and information.
Leverage AI to unleash innovation potential, accelerate innovation, and enhance R&D strategy.
Ideal Student is an intelligent chat assistant that provides convenient conversational services and an intelligent interactive experience.
Monica is an all-purpose assistant and understanding companion, providing intelligent dialogue services.
Anthropic
$21
Input tokens/M
$105
Output tokens/M
200
Context Length
Alibaba
$2
$20
-
Baidu
32
Google
$8.75
$70
1k
Bytedance
$0.5
Huawei
128
Openai
$14
$56
$0.7
$2.8
Minimax
$1.6
$16
Tencent
Xai
$1.05
$4.2
mradermacher
Diver-GroupRank-7B is a 7B parameter model specifically designed for paragraph sorting, text sorting, reasoning, and information retrieval. This version offers multiple quantization formats to suit different hardware and performance requirements.
A statically quantized version based on the AQ-MedAI/Diver-GroupRank-7B model, specifically designed for tasks such as paragraph sorting, text sorting, reasoning, and information retrieval. It offers multiple quantization levels to meet different hardware requirements.
LiquidAI
PyLate is a tool library focused on sentence similarity calculation and information retrieval. It can perform efficient information retrieval tasks on multiple datasets, providing strong support for research and applications in related fields. This model supports 8 languages and performs excellently in multiple benchmark tests.
Mungert
Fathom-Search-4B GGUF is a powerful tool designed for text generation tasks. It is generated based on specific base models and technologies and performs excellently in search-intensive benchmark tests. It can effectively solve the problems of long-cycle information retrieval and synthesis.
jinaai
jina-reranker-v3 is a multilingual document re-ranker with 0.6B parameters. It adopts an innovative 'Last but not least interaction' architecture and can efficiently and accurately re-rank documents in a multilingual environment, significantly improving the relevance and efficiency of information retrieval.
driaforall
This is an MLX version memory agent model with 8-bit precision, trained based on Qwen3-4B-Thinking-2507, specifically designed to handle information retrieval, update, and clarification tasks in the memory system.
ReasonRank-32B is a quantized version based on the liuwenhan/reasonrank-32B base model. It provides multiple quantized weight files and is specifically designed for tasks such as paragraph sorting, text sorting, inference, and information retrieval. This model has undergone static quantization processing and is suitable for various application scenarios.
MongoDB
mdbr-leaf-ir is a high-performance compact text embedding model developed by MongoDB Research specifically for information retrieval tasks. It is particularly suitable for the retrieval stage of the RAG pipeline. The model uses knowledge distillation technology, supports asymmetric architecture, MRL truncation, and vector quantization, and performs excellently in the BEIR benchmark test.
lightonai
PyLate is a sentence similarity model based on the ColBERT architecture, using Alibaba-NLP/gte-modernbert-base as the base model and trained with distillation loss, suitable for information retrieval tasks.
sdadas
MMLW is a neural text encoder for Polish, optimized for information retrieval tasks, capable of converting queries and paragraphs into 1024-dimensional vectors.
soob3123
A specialized variant of Google's Gemma 3 4B model, optimized for morally neutral information retrieval systems, avoiding response biases introduced by traditional alignment models.
RichardErkhov
A text ranking model fine-tuned based on Qwen2.5-0.5B-Instruct, suitable for information retrieval and relevance ranking tasks
A 50-million-parameter text reranking model based on the Qwen2.5 architecture, suitable for information retrieval and document ranking tasks
DISLab
Gen-8B-R2 is a generation model focused on reducing hallucination issues in RAG systems, particularly suitable for handling retrieval noise and information overload.
jhu-clsp
rank1 is an information retrieval reranking model trained on Qwen2.5-0.5B, improving relevance judgment accuracy through generated reasoning chains.
rank1-3b is an information retrieval re-ranking model trained on Qwen2.5-3B, which performs relevance judgments by generating reasoning chains
mohamed2811
An Arabic sentence transformer trained on Egyptian legal books and synthetic data, optimized for semantic text similarity and information retrieval tasks.
rank1-32b is an information retrieval reranking model based on Qwen2.5-32B, which judges relevance by generating reasoning chains
rank1 is a 14-billion-parameter reasoning re-ranking model that improves the performance of information retrieval tasks by generating explicit reasoning chains before making relevance judgments.
jfkback
Hypencoder is a hypernetwork model for information retrieval, consisting of a text encoder and Hypencoder. It can convert text into a small neural network and output relevance scores.
The Exa MCP Server is a server that provides web search capabilities for AI assistants (such as Claude), enabling real-time and secure web information retrieval through the Exa AI Search API.
Supermemory is an AI-driven memory engine designed to provide contextual knowledge for LLMs by integrating personal data, enabling intelligent management and retrieval of information.
A web research MCP server designed for Claude, providing real - time web information retrieval functions
A persistent memory server based on a knowledge graph, supporting cross - session storage and retrieval of user information
The YouTube MCP Server is a standardized interface implementation that allows AI language models to interact with YouTube content through protocols, providing functions such as video information retrieval, subtitle management, channel and playlist management.
The Medical MCP Server is a dedicated server based on the Model Context Protocol (MCP) that provides AI assistants with access to medical data and medical information tools, including functions such as drug information query, medical literature retrieval, and health topic access.
An MCP server for web research that integrates Google Search, web page content extraction, session tracking, and screenshot functions to help Claude conduct real-time information retrieval.
An MCP server that allows Claude Desktop to execute terminal commands, supporting command execution, directory navigation, and environment information retrieval.
The Wikipedia MCP Server is a tool that provides Wikipedia information query services for large language models. It enables real - time data access through a standardized protocol interface and includes functions such as searching, article retrieval, and summary generation.
The Pacman MCP Server is a model context protocol server that provides query functions for multiple software package indexes, supporting the search and information retrieval of software package repositories such as PyPI, npm, crates.io, Docker Hub, and Terraform Registry.
This project is an integrated MCP server suite with various functions, including media tools, information retrieval, PDF generation, and presentation creation services, which need to be configured and run separately.
A recipe query service based on the MCP protocol, supporting the retrieval of all dish lists and specific recipe information.
The YouTube MCP Server is a service that implements the Model Context Protocol (MCP). It provides a standardized interface for AI language models to interact with YouTube content, supporting functions such as video information retrieval, subtitle management, channel and playlist operations, etc.
An MCP server that provides news retrieval and search functions for The Verge
Implementation of the Twitter MCP service, providing API integration functions such as tweet posting, searching, and user information retrieval.
An MCP server based on the Gemini API and Google Search, which provides intelligent answering functions for the latest information when used in conjunction with an AI assistant (such as Cline).
ArtistLens is a powerful MCP server that provides access to the Spotify Web API, supporting functions such as music search, artist information retrieval, and playlist management.
The MCP service of Bangumi TV provides access to the BangumiTV API, supporting queries for information on entries such as anime, manga, music, and games, including entry details, characters, personnel, and related data retrieval functions.
aica is an open - source, customizable, cross - platform AI code analysis tool that supports functions such as code review, automatic knowledge retrieval, and commit information generation, and can be integrated with GitHub Actions.
MCP-Memos is a memo tool based on the MCP protocol, designed specifically for developers. It supports quick recording and retrieval of text information without switching applications. It uses large language models to provide powerful fuzzy search capabilities, including semantic understanding, context awareness, and natural language query functions.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
