Recently, Tongyi Lab of Alibaba officially released its latest end-to-end speech recognition large model - FunAudio-ASR. The biggest highlight of this model is its innovative "Context Module," which significantly improves the accuracy of speech recognition in high-noise environments. The hallucination rate has been reduced from 78.5% to 10.7%, a decrease of nearly 70%. This technological breakthrough has set a new benchmark for the speech recognition industry, especially suitable for noisy environments such as meetings and public places. FunAudio-AS
mcp-agent is officially released. As a lightweight framework based on the Model Context Protocol (MCP), it aims to provide developers with a simplified solution for building intelligent agent applications. This framework not only seamlessly integrates with other MCP services but also boasts high composability and customizability, allowing developers to focus on core business logic implementation without being bogged down by complex system architecture. mcp-agent is designed to be simple and efficient, removing redundant modules found in traditional frameworks to provide a lightweight experience.
In the context of the increasing integration of AI technology into the entertainment industry, Kugou Music and DeepSeek, a leading domestic AI company, have established a strategic partnership. This collaboration leverages large language models to revolutionize music platforms, transforming them from mere "tool-based applications" into "intelligent entertainment hubs." This transformation is centered around four core AI functional modules that are comprehensively reshaping the entire music consumption experience, setting a new benchmark for AI and music integration.
Google Research recently announced the innovative 'Titans' series model architecture, achieving a groundbreaking 2 million token context length through bionic design, with plans to open-source related technologies in the future. The core innovation of this architecture is the introduction of a Deep Neural Long-Term Memory Module, inspired by the human memory system. Titans cleverly combines the rapid response capability of short-term memory with the persistence characteristics of long-term memory, while utilizing an attention mechanism to handle immediate context, forming an efficient information processing system.
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
$7.7
$30.8
200
-
Anthropic
$105
$525
$0.7
$7
$35
$17.5
$21
Alibaba
$2
$20
$4
$16
Baidu
128
$6
$24
256
$1
$10
DavidAU
This is a mixture-of-experts model based on Qwen3-Coder-30B-A3B-Instruct, with 54 billion parameters and a context length of 1 million. The model has powerful programming capabilities and general scenario processing capabilities through three-step merging and Brainstorm 40X optimization. It is especially integrated with a thinking module, which can perform in-depth reasoning before answering.
smp-test-models
PSPNet is a deep learning model for semantic segmentation that uses pyramid pooling modules to capture multi-scale contextual information
Karko
Proctora is a model based on the Mixture of Experts (MoE) architecture, combining expert modules for role-playing and factual responses, supporting a 32K context length, and excelling in AI-RPG evaluations.
A NestJS module for easily exposing AI tools, resources, and prompts via the Model Context Protocol (MCP), supporting multiple transport types and automatic discovery and registration functions.
The Terrakube MCP Server is a Model Context Protocol server for managing Terrakube operations, providing comprehensive API integration for workspace, variable, module, and organization management.
A set of lightweight programs including weather services and financial analysis modules, providing specific functions through a standardized model context protocol.
This project includes the Cloud Security Alliance Model Context Protocol server, covering various functional modules and service interfaces.
MCP Mediator is a Java - based implementation of the Model Context Protocol (MCP) mediator, providing seamless integration between MCP clients and servers, supporting efficient communication and tool execution. The project includes core modules, examples, and various service integrations, supports quickly converting existing code into MCP services through annotations, and has the ability to proxy multiple servers.
This project includes the Cloud Security Alliance model context protocol servers, covering various functional modules and service interfaces, including multiple useful tools imported from Anthropic and chat services provided by CSA.
This project enables large language models to directly understand and generate audio effect modules in the Max audio processing software through the Model Context Protocol (MCP). It supports explaining, modifying, and creating audio effect modules and provides an interaction interface with LLMs.
This project integrates Claude AI with Pure Data through the Model Context Protocol, supporting dynamic creation, modification, and control of Pure Data audio processing modules through natural language.
The Terrakube MCP Server is a model context protocol server developed based on TypeScript, designed specifically for the Terrakube platform, providing functions such as workspace management, variable handling, module operations, and organization management.
This project provides a series of example modules using the AWS Model Context Protocol (MCP), covering multiple languages and technology stacks, including TypeScript, Python, Spring AI, etc., demonstrating the application of MCP in scenarios such as client-server communication, ECS deployment, and RAG integration.
A fully functional MCP server that offers 73 tools covering 11 modules including file system, diagnostics, scripts, time management, network, context, Git operations, user input, version control, clipboard, and text conversion.
The Claude-LaTeX MCP integration project connects Claude AI with LaTeX editors through Anthropic's Model Context Protocol (MCP), providing AI - assisted functions for academic writing, science fiction creation, and philosophical writing, including core tools such as formula generation, document structure optimization, and reference management, as well as professional extension modules for different types of content.
The NestJS MCP module is an integration module designed for the NestJS framework to simplify the implementation of the Model Context Protocol (MCP) server. It supports multiple transport layers (including STDIO and HTTP/SSE) through decorators (such as @McpResource, @McpTool, @McpPrompt) and familiar NestJS patterns, enabling developers to quickly build MCP - compatible services.
This project provides a series of Model Context Protocol (MCP) servers for enhancing the external capabilities of AI assistants, including independent implementation modules for specific functions such as educational course queries.
A NestJS module for creating MCP (Model Context Protocol) services that support Server-Sent Events (SSE) transmission, providing functions such as automatic discovery of tools and resources, request validation, and progress notification.
Lex is a TypeScript framework that provides situational memory and architecture awareness for AI agents, solving the problem of context loss in long - process development. Through memory snapshots, module dependency navigation, and architecture policy execution, it enables AI assistants to remember work progress and understand code structure.
This project is a development environment integrating the ModelContextProtocol (MCP) SDK and servers. It manages the Python and TypeScript SDKs and officially maintained servers through Git sub - modules, aiming to provide basic context and tool support for developing new MCP servers.
MCP Server is a Model Context Protocol server module developed for Rhymix CMS, providing a standardized interface for AI clients to access Rhymix data and functions, and supporting custom tool development and automatic plugin scanning.
The @cmmv/mcp module of CMMV implements the Model Context Protocol (MCP), providing a standardized interface for CMMV applications, supporting the interaction between LLMs and applications, and including functions such as tool registration, validation, and connection management.
This project is a collection of multiple Model Context Protocol (MCP) servers, aiming to provide dedicated interfaces for large language models. These servers are created by non - professional developers with the help of AI tools and currently include two functional modules: Perplexity search integration and keyword analysis.
%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)
