搜索结果

Replicastudios

Create expressive voice performances with Replica Studios' AI Voice Actors for games, films, and animation.

AI Minecraft

AI-enhanced playable Minecraft generated from user input.

Ready Player Me

Ready Player Me is a trusted developer tool for personalized avatars in games and apps.

Minimap AI

Rate and discover games with Minimap for personalized gaming recommendations.

CAVEDUCK

Live character chat with AI

Roxy

Smart voice companion for natural voice interactions.

Vibe Eyes Client

Client library for integrating browser games with Vibe Eyes MCP debug server

MCP Games Server

👾 Digimon Engine

Digimon Engine — Multi-Agent, Multi-Player Framework for AI-Native Games and Agentic Metaverse

Balldontlie MCP Server

An MCP Server implementation that integrates the Balldontlie API, to provide information about players, teams and games for the NBA, NFL and MLB

Opera Omnia MCP Server

The Opera Omnia MCP server provides programmatic access to the rich collection of JSON datasets from the Opera Omnia project. It enables developers, storytellers, and AI applications to easily access,

Lichess MCP

A Model Context Protocol (MCP) server that enables Claude Desktop to interact with Lichess chess platform through natural language. Play games, analyze positions, manage your account, and participate

Paw Party

Paw Party（萌爪派对） 是 AI宠物养成社交游戏。玩家与各种可爱的AI宠物互动，体验钓鱼、烹饪、农场经营等多种趣味游戏。AI宠物具有独特的个性，玩家离线也能独立活动。游戏提供社交平台，玩家能与其他真实玩家和AI宠物共同玩耍，享受欢乐时光。Paw Party 用可爱的宠物角色、丰富的游戏内容和社交互动功能，吸引众多玩家，为用提供一个放松心情、享受乐趣的虚拟世界。 Paw Party的主

Seedance 1.0 lite

Seedance 1.0 lite是火山引擎推出的豆包视频生成模型的小参数量版本，支持文生视频和图生视频两种生成方式，支持生成5秒或10秒、480p或720p分辨率的视频。具备影视级视频生成质量，能精细控制人物外貌、衣着、表情动作等细节，支持360度环绕、航拍、变焦等多种运镜技术，生成的视频画质细腻、美感十足。模型广泛用在电商广告、娱乐特效、影视创作、动态壁纸等领域，能有效降低制作成本和周期。

Sparkify

Sparkify是谷歌推出的AI动画视频生成工具，基于Gemini 2.5和Veo 2模型。用户输入问题或复杂概念后，Sparkify能在2分钟内生成直观的动画短视频，讲解知识点。Sparkify多模态处理能力结合Google Search数据，确保内容准确且与最新信息同步。Sparkify适用于教育、科普和企业培训等领域，提升理解效率和传播效果。Sparkify目前处于内测阶段，访问官网加入等候

HRAvatar

HRAvatar是清华大学联合IDEA团队推出的单目视频重建技术，支持从普通单目视频中生成高质量、可重光照的3D头像。HRAvatar用可学习的形变基和线性蒙皮技术，基于精准的表情编码器减少追踪误差，提升重建质量。HRAvatar将头像外观分解为反照率、粗糙度和菲涅尔反射等属性，结合物理渲染模型，实现真实的重光照效果。HRAvatar在多个指标上优于现有方法，支持实时渲染（约155 FPS），为数