Sponsored by Deepsite.site, Most Affordable AI Code Agent Powered by DeepSeek.
Build, test, debug, and interact with desktop and mobile applications with the Tauri framework. Screenshots, DOM state, and console logs from your running app give the AI rich context to understand what's happening—and tools to interact with it.
**Context Keeper** 基于LLM驱动的智能上下文记忆管理系统,专为AI Agent提供企业级记忆能力。 **核心创新**:独创"宽召回+精排序"架构,通过两阶段LLM协作实现多维度检索融合(向量+时间线+知识图谱),准确率从传统RAG的45%提升至**75%+**,召回率达**80%+**。 **技术亮点**:完整实现MCP协议(HTTP/WebSocket/SSE三种传输),四维统一上下文模型(Project/Topic/Conversation/Code),支持短期/长期记忆智能转换。 **性能表现**:10000+ QPS并发能力,P95延迟<500ms,用户/工作空间完全隔离。 **开源生态**:MIT许可,Go语言实现,深度集成Cursor/VSCode IDE。让AI助手真正拥有持续记忆能力,告别重复解释,开启智能协作新时代。
An MCP (Model Context Protocol) server that wraps gopls to provide Go language server features.
prototype MCP server around generating PNG from ZPL so that agents can iterate better on results when someone asks me to build a really complex ZPL label layout
interactive programming of melodies, producing MIDI
Shrimp Task Manager 透過結構化的工作流程引導,協助 Agent 系統性規劃程式開發步驟,強化任務記憶管理機制,有效避免冗餘與重複的編程工作。
a powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & Agno integration)
Mirror of
A powerful Model Context Protocol (MCP) server that manages and serves programming guidelines and rules. This server integrates with development tools to provide consistent coding standards across projects.