Level-Navi Agent is an open-source general-purpose web search agent framework that can decompose complex problems and progressively search for information on the internet until it answers user questions. By providing the Web24 dataset, covering five major fields: finance, games, sports, movies, and events, it provides a benchmark for evaluating model performance on search tasks. The framework supports zero-shot and few-shot learning, providing an important reference for the application of large language models in the field of Chinese web search agents.

Chat2Geo is a web application built on Next.js 15 that provides a ChatGPT-like chat interface for performing remote sensing-based geospatial analysis. It leverages Google Earth Engine to process and analyze various remote sensing datasets in the backend. Users can upload their own vector data, run advanced geospatial queries, and integrate with an AI assistant to complete tasks such as land cover mapping, change detection, and air pollutant monitoring. By combining geospatial analysis with non-geospatial/textual information, this product offers a powerful and practical Knowledge Retrieval Augmented Generation (RAG) workflow. It inherits most of the building blocks of the GRAI 2.0 application developed by GeoRetina and is continuously updated to meet community needs.

Site RAG is a Chrome extension designed to assist users in quickly obtaining answers to questions while browsing the web, using natural language processing technology. It supports querying with the current page content as context and allows the indexing of entire website content into a vector database for subsequent retrieval-enhanced generation (RAG). The product runs entirely in the local browser, ensuring user data security, and supports connection to a locally running Ollama instance for inference. It primarily targets users who need to rapidly extract information from web content, such as developers, researchers, and students. This product is currently offered for free, making it suitable for those seeking immediate assistance while browsing the web.

node-DeepResearch is a deep research model based on Jina AI technology, focused on finding answers to questions through continuous searching and reading of web pages. It leverages the LLM capabilities provided by Gemini and the web search functionality of Jina Reader to handle complex query tasks and generate answers through multi-step reasoning and information integration. The main advantages of this model lie in its powerful information retrieval and reasoning capabilities, enabling it to address complex questions requiring multi-step answers. It is suitable for scenarios requiring in-depth research and information mining, such as academic research and market analysis. Currently, this model is open-source, and users can obtain the code from GitHub for self-deployment.

PaSa is an advanced academic paper search agent developed by ByteDance, based on large language model (LLM) technology. It can autonomously invoke search tools, read papers, and filter relevant references to obtain comprehensive and accurate results for complex academic queries. This technology is optimized through reinforcement learning, trained using the synthetic dataset AutoScholarQuery, and has shown outstanding performance on the real-world query dataset RealScholarQuery, significantly outperforming traditional search engines and GPT-based methods. The main advantages of PaSa lie in its high recall and precision rates, providing researchers with a more efficient academic search experience.

vdr-2b-multi-v1 is a multilingual embedding model launched by Hugging Face, specifically designed for visual document retrieval. This model encodes document page screenshots into dense vector representations, allowing for the search and query of visually rich multilingual documents without the need for OCR or data extraction processes. Developed based on the MrLight/dse-qwen2-2b-mrl-v1 model, it has been trained on a self-constructed multilingual query-image pair dataset, making it an upgraded version of mcdse-2b-v1 with enhanced performance. The model supports Italian, Spanish, English, French, and German and includes a high-quality open-source multilingual synthetic training dataset with 500,000 samples, characterized by low VRAM usage and fast inference capabilities, demonstrating excellent performance in cross-language retrieval.

Open Deep Research is an open-source tool designed to generate detailed reports from web search results using AI technology. It integrates technologies like the Bing Search API and JinaAI, enabling rapid retrieval and processing of large amounts of information to generate customized reports. The tool's primary advantages are its flexibility and open-source nature, allowing users to tailor and expand it according to their needs. It is suitable for users who need to organize and analyze significant amounts of information, including researchers, analysts, and corporate users. This project is currently free, making it accessible for organizations and individuals of all sizes.

OpenScholar is a retrieval-augmented language model (LM) designed to assist scientists in effectively navigating and synthesizing scientific literature by first searching for relevant papers and then generating answers based on those sources. This model is significant for managing the millions of scientific papers published each year and helps scientists find the information they need or keep up with the latest discoveries in specific subfields.

Prompt Monitor is an AI search optimization tool that helps businesses enhance brand awareness and sales by monitoring brand exposure in AI recommendations. This tool can track brand exposure on AI platforms, perform competitive analysis, monitor brand mentions, perform sentiment analysis, discover citations, identify AI sources, and track rankings.

AurumTau is an intelligent, context-aware search engine based on advanced AI technology that provides intelligent, context-aware answers. Its main advantages lie in providing accurate and fast answers to help users solve problems.

Opera Neon is an intelligent AI browser that can understand user intentions, assist in completing tasks, and provide intelligent assistance. Its main advantages include automated tasks, understanding intentions and outputting, and collaborating with users. Opera Neon is positioned to provide an intelligent browsing experience and is currently in the beta testing phase.

Morphik is an open-source AI knowledge base that helps users obtain answers from research papers, reports, company files, etc. Its search function is fast and accurate, with outstanding performance in technical field searches. Morphik can connect to any data source and supports perfect searching of complex charts, diagrams, and data tables.

Unoffended Labs is a shopping experience platform that provides AI recommendation and intelligent search functions. It offers personalized shopping experiences for users by helping them quickly find their favorite items.

Perigon is a platform focused on real-time data search and analysis. Its unique Omnibar search bar allows users to quickly query information on any topic and track data dynamics in real time. The product is primarily aimed at business users who need to quickly access and analyze large amounts of information, such as market analysts, researchers, and business decision-makers. Its powerful search functionality and flexible customization options allow users to quickly find valuable information based on their needs and track key data by creating signals and workflows. Perigon offers flexible pricing plans to meet the needs of users of different scales.

Level-Navi Agent is an open-source general-purpose web search agent framework that can decompose complex problems and progressively search for information on the internet until it answers user questions. By providing the Web24 dataset, covering five major fields: finance, games, sports, movies, and events, it provides a benchmark for evaluating model performance on search tasks. The framework supports zero-shot and few-shot learning, providing an important reference for the application of large language models in the field of Chinese web search agents.

Phind is an advanced AI-powered search tool that helps users quickly access information through multi-turn conversations and multilingual support. It supports various search methods, including text, voice, and image searches, providing more precise search results. Phind's key advantages are its powerful natural language processing capabilities and multilingual support, catering to diverse user needs. This product is positioned as a high-end intelligent search tool, suitable for users who need to efficiently access information.