Open-source AI agent firewall for MCP security: agent egress control, DLP, SSRF, and prompt injection defense.

im busy building ai agents so why not let an ai talk to my girlfriend? (i am single)

Hybrid RAG with structured Docling data, multiple embedding providers, and multi-agent workflows packaged as an extensible AI assistant toolkit.

A Model Context Protocol (MCP) server that orchestrates queries across multiple Ollama models, synthesizing their insights to deliver a comprehensive and multifaceted AI perspective on any given query.

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

Unified MariaDB access with read-only SQL, vector embeddings, and optional vector store for semantic search, supporting OpenAI, Gemini, and HuggingFace.

Use Kokoro text to speech to convert text to MP3s with optional autoupload to S3.

A code-first, composable SDK to build powerful AI agents

Entroly-Daemon: Self-Evolving Daemon. Compress 2M-token repos into a razor-sharp Principal Engineer's context. 85–99% fewer tokens, 100% accuracy retention (verified by live API benchmarks). Built for Cursor, Claude Code, Opus, Codex, GPT & Custom Providers.

SAFE-MCP is a comprehensive security framework for documenting and mitigating threats in the AI Agent ecosystem.

"AnyTool: Universal Tool-Use Layer for AI Agents"

Run MATLAB® using AI applications with the official MATLAB MCP Server from MathWorks®. This MCP server for MATLAB supports a wide range of coding agents like Claude Code® and Visual Studio® Code.

Official Docker MCP registry

Config-driven backtester with AI-assisted NL agents, multi-market support, and a rich strategy library.

Universal content summarization across text, web, PDFs, EPUBs, and HTML with customizable length and multi-language support.

2025 年 AI 编程助手实战项目（作者：程序员鱼皮），基于 Spring Boot 3.5 + Java 21 + LangChain4j + AI 构建智能编程学习与求职辅导机器人，覆盖 AI 大模型接入、LangChain4j 核心特性、流式对话、Prompt 工程、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、Web 爬虫、安全防护、Vue.js 前端开发、SSE 服务端推送等企业级 AI 应用开发技术。帮助开发者掌握 AI 时代必备技能，熟悉 LangChain 框架，提升编程学习效率和求职竞争力，成为企业需要的 AI 全栈开发人才。

A minimalist, modular AI agent framework with Model Context Protocol support, enabling rapid agent assembly, memory, tools, RAG, and on-chain integrations.

Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.

OS-agnostic, model-agnostic desktop automation server. Gives any AI agent eyes, hands, and ground-truth verification on Windows, macOS, and Linux.

AI‑powered YouTube uploader—no CLI, no YouTube Studio.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

Agentic RAG for any scenario. Customize sources, depth, and width

Local AI engine for Apple Silicon enabling offline multi-model LLM/VLM/image generation with OpenAI/Anthropic compatibility and advanced caching.

Architectural intelligence layer for AI coding agents. Structural graph, architecture governance, multi-agent orchestration, vulnerability mapping. 139 commands, 101 MCP tools, 26 languages, 100% local.