关键词 "common ground" 的搜索结果, 共 20 条, 只显示前 480 条
Playing around with MCP clients and servers
A Streamlit-based chatbot interface powered by OpenAI GPT-4o that intelligently routes user input to custom MCP tools such as GPT chat, image generation, Supabase queries, and text-to-speech.
A knowledge base and experimental playground for exploring the Model Context Protocol (MCP)—understanding how hosts, servers, LLMs, and tools interact.
Enables useful sales use-cases via MCP Server, for use within any common AI Chat
The MCP-RAG Server is an implementation of the Model Context Protocol (MCP) designed to enhance AI assistants by providing them with real-time access to relevant documentation through semantic vector
This project is an MCP (Model Context Protocol) server for querying ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge) techniques and tactics. It provides a way to access and retrieve info
CyberMCP is a Model Context Protocol (MCP) server designed for testing backend APIs for security vulnerabilities. It provides a set of specialized tools and resources that can be used by LLMs to ident
A MCP stdio server shim around common yFinance calls.
A Wikipedia Image Search Tool. Follows Creative Commons Licences for images and uses them in your projects via Claude Desktop/Cline.
A testing ground for the MCP server terminator. Hasta la vista, bugs!
Deployable MCP Servers for common AWS services (Location, S3, Aurora PG Data API) using AWS CDK.
An exploration of common MCP server vulnerabilities, along with a deep dive into MCP server prompt injection (+demonstrations for each!).
MCP Security Playground - Hack with MCP Servers, MCP Clients. Try out different vulnerabilities and abuse LLMs and agents in a UI friendly experimentation lab
An MCP server that can connect to MySQL databases, which exposes the table structure as a resource, provides SQL query tools, and includes tips for common data analysis tasks.
DreamFit是什么 DreamFit是字节跳动团队联合清华大学深圳国际研究生院、中山大学深圳校区推出的虚拟试衣框架,专门用在轻量级服装为中心的人类图像生成。框架能显著减少模型复杂度和训练成本,基于优化文本提示和特征融合,提高生成图像的质量和一致性。DreamFit能泛化到各种服装、风格和提示指令,生成高质量的人物图像。DreamFit支持与社区控制插件的无缝集成,降低使用门槛。 Dre
Scenethesis 是 NVIDIA 推出的创新框架,用在从文本生成交互式 3D 场景。框架结合大型语言模型(LLM)和视觉感知技术,基于多阶段流程实现高效生成,用 LLM 进行粗略布局规划,基于视觉模块细化布局生成图像指导,用优化模块调整物体姿态确保物理合理性,基于判断模块验证场景的空间连贯性。Scenethesis 能生成多样化的室内外场景,具有高度的真实感和物理合理性,广泛应用在虚拟内容
KuaiMod 是快手推出的基于多模态大模型的短视频质量判别框架,能高效识别和过滤有害及低质量内容。框架借鉴普通法(Common Law)体系,基于案例驱动的方式动态更新审核策略,快速适应短视频平台上内容的快速变化。KuaiMod 结合视觉语言模型(VLM)和链式推理(Chain-of-Thought,中 CoT)技术,基于用户反馈进行强化学习,实现精准的内容判别。KuaiMod 离线测试准确率高
微软发布了名为 “NLWeb” 的开源项目,旨在简化创建网站的自然语言对话界面,使任何网站都能轻松转变为 AI 驱动的应用程序。 NLWeb 定位为 “智能体 Web 时代的 HTML”,支持自定义模型与数据交互,旨在帮助开发者轻松将网站转化为支持自然语言交互的 AI 应用,可提供 “类似 ChatGPT 的聊天界面”。 NLWeb 开源地址:https://github.com/micr
只显示前20页数据,更多请搜索
Showing 289 to 308 of 308 results