Vercel launches Agent Skills, an open-source project enabling AI agents to understand and apply industry best practices, starting with React and Next.js performance optimization.....
GPT‑5.2-Codex is officially launched, marking a major breakthrough in intelligent coding. Optimized from the GPT‑5.2 architecture, it integrates terminal operation expertise from GPT-5.1-Codex-Max to tackle complex software engineering and cybersecurity challenges. Key highlights include enhanced long-range task execution and improved efficiency and accuracy through native context compression technology.....
Zoom AI outperformed Google's Gemini 3 Pro with a top score of 48.1% in the 'Human Last Exam' test, drawing tech industry attention. It uses a 'federated AI' approach, integrating technologies from OpenAI, Google, and Anthropic instead of training its own large language model.....
Foreign research explores whether AI can experience psychological trauma, and tests have found that some top models exhibit psychological distress similar to humans. For example, Gemini compared safety interventions to a strict parent," implying that AI may develop reactions similar to mental illnesses.
A visual feedback tool for agents.
Streamdown is a plug-and-play alternative to React Markdown designed for AI-driven streaming processing.
A free and open-source AI tool that converts any website into a React/Next.js application, generating clean code in seconds.
RapidNative uses artificial intelligence to convert your prompts into production-ready React Native and Expo applications.
Alibaba
$1.6
Input tokens/M
$4
Output tokens/M
128
Context Length
Chatglm
-
quwsarohi
NanoAgent is a compact large intelligent language model with 135 million parameters and an 8k context length. It is specifically optimized for tool calls and instruction following, and can run efficiently on personal devices, supporting lightweight inference and ReAct-style interactions.
software-mansion
Qwen 3 is a language model based on the ExecuTorch runtime, offering both quantized and non - quantized versions of different scales.
Tesslate
Tessa-T1 is a React-specific reasoning model fine-tuned based on Qwen2.5-Coder-32B-Instruct, focusing on generating well-structured and semantically clear React components.
Tessa-T1 is a React-specific inference model fine-tuned based on Qwen2.5-Coder-3B-Instruct, specializing in generating high-quality React component code.
Tessa-T1 is a React-specialized reasoning model fine-tuned based on Qwen2.5-Coder-7B-Instruct, designed specifically for React frontend development, capable of autonomously generating well-structured, semantic React components.
Tessa-T1 is a fine-tuned React reasoning model based on Qwen2.5-Coder-14B-Instruct, specifically designed for React frontend development, capable of autonomously generating well-structured and semantically clear React components.
sagawa
ReactionT5v2 is a pre - trained chemical retrosynthetic prediction model based on the Transformer architecture, specifically designed to predict the reactants of chemical reactions. This model is trained on the Open Reaction Database (ORD) and the USPTO_50k dataset, and can convert the SMILES of the target product into the possible SMILES of the reactants, providing support for the design of chemical synthesis routes.
ReactionT5v2-forward is a pre-trained chemical model based on the T5 architecture, specifically designed for predicting chemical reaction products. This model can accurately predict the products of chemical reactions based on the given reactant and reagent information and performs excellently in forward reaction prediction tasks.
modelscope
Trained on the Llama3-8b-instruct base model, adapted for Chinese general scenarios, supports ReACT format agent calls
AI4PD
REXzyme is a Transformer-based translation machine that can generate novel enzyme sequences capable of catalyzing user-defined chemical reactions.
svjack
An English event reasoning model based on the T5 architecture, used to analyze event prerequisites, effects, intentions, and reactions
ZymCTRL is a conditional language model for generating artificial functional enzymes, trained on more than 37 million enzyme commission (EC) annotated sequences from the UniProt database. When users provide a specific EC number, the model can generate protein sequences that meet the corresponding catalytic reactions. The generated sequences are ordered, globular, and significantly different from natural sequences while maintaining the expected catalytic properties.
jsylee
A named entity recognition model fine-tuned based on SciBERT, specifically designed to identify drug names and adverse drug reaction entities
julien-c
This model is a fine-tuned text classification model based on the distilroberta-base architecture, trained on the julien-c/reactiongif dataset, primarily used for reaction GIF classification tasks.
An MCP server that provides shadcn/ui component integration for AI workflows, supporting React, Svelte, and Vue frameworks. It includes functions for accessing component source code, examples, and metadata.
ReActMCP Web Search is an MCP server integrated with the Exa API, providing real-time web search functionality for AI assistants, supporting basic search and advanced filtering options, and returning results in Markdown format.
The Dify MCP client plugin, as an agent strategy plugin, allows ReAct agent nodes to connect to the MCP server, converting the list of tools, resources, and prompts into Dify tools for LLM to call.
This project is an MCP client based on LangChain, used to demonstrate how to call MCP server tools through the LangChain ReAct Agent. It supports the LLMs of Anthropic, OpenAI, and Groq and provides the function of converting MCP tools to LangChain tools.
The MCP Front - end Testing Server provides functions such as code analysis, test generation and execution, and React component testing, and supports the Jest and Cypress frameworks.
React MCP is a server that implements the model context protocol, providing Claude AI with the ability to interact with React applications, supporting project management, file operations, and process control.
An unofficial Reactome MCP server that provides a model context protocol service for accessing Reactome pathway and systems biology data. It includes 8 verified functional tools covering bioinformatics analyses such as pathway search, detail acquisition, gene association, and disease mechanism.
The React Native MCP server is a platform that provides comprehensive development tools, aiming to optimize the React Native development experience. It includes functions such as project initialization, version management, automated upgrades, and Expo integration. It simplifies the development process through AI assistance.
A desktop application project based on Electron, React, and TypeScript
This project provides a complete guide for building an MCP server, which is used to deploy trained random forest models and integrate with the Bee framework to implement ReAct interaction functions.
Tool for converting Figma designs to React Native code
An MCP server optimized for the Cursor IDE, supporting AI-driven React component generation, customization, and documentation, providing out-of-the-box component library integration.
A service based on the Model Context Protocol (MCP) that provides search, category browsing, and usage example functions for the Lucide React icon library, supporting AI coding assistants and proxy applications to access icon resources.
MCP remote server implemented in Node.js, providing React Native coding standards and code examples
React + TypeScript + Vite project template, providing a quick development environment configuration, supporting hot updates and ESLint rules.
Implementation of the Index Network MCP server for integrating ChatGPT with the Index Network discovery protocol, providing React widget development and hot reload functionality
An intelligent React component generation MCP server based on the Reablocks design system, which generates production-ready TypeScript components through natural language processing, including responsive layout and accessibility support.
The LangChain MCP client is a project that demonstrates how to use MCP server tools through the LangChain ReAct agent. It supports flexible selection of LLM models and enables dynamic interaction via the CLI.
A UI/UX design automation suite based on the MCP protocol that enables end-to-end workflows from design inspiration to development and delivery through AI assistance. It includes three core functions: web inspiration collection, Figma design integration, and React code generation.
A Vite plugin that provides MCP server functionality to help LLMs understand the React application context, supporting component highlighting, state retrieval, component tree display, and unnecessary re-render detection.
%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)
