搜索结果

repo-template

A Python server implementation for Feishu (Lark) bot that follows the Model Context Protocol (MCP). This server provides a standardized interface for handling automated messaging and context-aware int

NATS MCP Server

MCP server for NATS messaging system using NATS CLI - enabling AI agents to interact with NATS messaging

WeCom Bot MCP Server

A Python server implementation for WeCom (WeChat Work) bot that follows the Model Context Protocol (MCP). This server provides a standardized interface for handling automated messaging and context-awa

MedifinderMCP Server

Message Communication Protocol (MCP) server that facilitates secure, standardized communication between system components and the medicine inventory database. Provides RESTful endpoints for location-b

Sensei MCP

Sensei MCP is a Model Context Protocol (MCP) server that provides expert guidance for Dojo and Cairo development on Starknet.

Model Context Protocal (MCP) Implementation

This is a simple MCP Server Framework that enables data to be passed through a structured messaging protocol, allowing seamless communication between clients and servers. It supports efficient data ex

Slack

Channel management and messaging capabilities

Telnyx Local Model Context Protocol (MCP) Server

Official Telnyx Local Model Context Protocol (MCP) Server that enables interaction with powerful telephony, messaging, and AI assistant APIs. This server allows MCP clients like Claude Desktop, Cursor

ClickSend MCP Server

MCP Server for Messaging using ClickSend

Twilio Messaging MCP Server

Mirror of

Twilio Messaging MCP Server

Matrix-Game

昆仑万维正式开源（17B+）Matrix-Game大模型，即Matrix-Zero世界模型中的可交互视频生成大模型。Matrix-Game是Matrix系列在交互式世界生成方向的正式落地，也是工业界首个开源的10B+空间智能大模型，它是一个面向游戏世界建模的交互式世界基础模型，专为开放式环境中的高质量生成与精确控制而设计。 空间智能作为AI时代的重要前沿技术，正在重塑我们与虚拟世界的

MMaDA

MMaDA（Multimodal Large Diffusion Language Models）是普林斯顿大学、清华大学、北京大学和字节跳动推出的多模态扩散模型，支持跨文本推理、多模态理解和文本到图像生成等多个领域实现卓越性能。模型用统一的扩散架构，具备模态不可知的设计，消除对特定模态组件的需求，引入混合长链推理（CoT）微调策略，统一跨模态的CoT格式，推出UniGRPO，针对扩散基础模型的统

MeanFlow

全新的生成模型MeanFlow，最大亮点在于它彻底跳脱了传统训练范式——无须预训练、蒸馏或课程学习，仅通过一次函数评估（1-NFE）即可完成生成。 MeanFlow在ImageNet 256×256上创下3.43 FID分数，实现从零开始训练下的SOTA性能。 图1（上）：在ImageNet 256×256上从零开始的一步生成结果 在ImageNet 256×25