Search

🤖 AI-powered Digital Marketing Assistant — content creation, strategy, research & analytics via Telegram. Bilingual EN/ID, Notion integration, pluggable LLM, security-hardened.

A free, open-source LLM security proxy. Drop it between your app and any LLM provider to get rate limiting, audit logging, token tracking, and Prometheus metrics with no code changes to your app.

Next-Generation Multi-Agent Collaboration Platform and Workflow Engine. Build and orchestrate production-ready AI agent teams with sandboxed execution, hybrid RAG, and enterprise-grade security.

"An advanced AI-powered framework for automated bug bounty hunting and security research. Featuring autonomous reconnaissance, multi-model LLM integration, and real-time reporting via Telegram and CLI."

OpenEnv-compliant RL environment for autonomous vulnerability patch management. Trains AI agents to balance security patching with uptime in complex dependency graphs. Meta PyTorch OpenEnv Hackathon 2026.

Production-grade MCP server for filesystem and git operations. 18 tools for AI agents (Claude, Cursor, etc). Features: path allowlisting security, Docker support, full test suite.

Drop-in preflight guard for AI agents — one call to the x402 Trust Layer (guard + security grade + attestation) before any paid x402_fetch. Works with any agent framework (LangChain, CrewAI, Coinbase AgentKit).

Use the idea of CLI as foundation, integrating the server structure of MCP and the efficiency attributes of Agent Skills, dedicated to build a high performance AI Agent architecture with good reliability, security, and compatibility.

An AI-Native commerce protocol enabling autonomous agents to browse, checkout, and transact securely using Razorpay's Official MCP Server, UPI Reserve Pay (SBMD), and LangGraph human-in-the-loop gates

Full-chain software development agent system for Claude Code — 6 master agents, 25 sub-agents & 96 atomic skills covering product, dev, QA, testing, ops & security.

Banking AI Agent with MCP & RAG - Production-ready customer service assistant using Google ADK, Model Context Protocol for secure data access, and Retrieval Augmented Generation for product knowledge

🤖 Cross-platform Personal Zalo AI Assistant powered natively by Google Antigravity & Gemini. Features 30-min guest token security and 1-click startup without API key.

Elevate your AI assistants (like Claude & Cursor) into autonomous cybersecurity experts. Pentester-MCP integrates 200+ pentesting tools via the Model Context Protocol (MCP) using a secure Docker sandbox.

Secure MySQL MCP Server with Clean Architecture. Enables AI assistants (Cursor, Copilot, Cline) to safely interact with MySQL/MariaDB databases, featuring RBAC, audit logging, and intelligent query validation.

AI-powered personal assistant framework built on AgentOS, forked from OpenClaw channels/integrations/bridges - adaptive agents with HEXACO personality, multi-channel communication, hierarchical inference, and human-in-the-loop security

Production-ready Agent Client Protocol (ACP) adapter for Cursor CLI with comprehensive tool system, security framework, and seamless AI-powered coding assistance in ACP-compliant editors like Zed

Agent Skills for AI coding assistants (Claude Code, Cursor, Copilot) — teaches MapQuest API best practices: geocoding, directions, static maps, search-ahead, store locators, traffic, and key security.

Client-facing design documents in Word (architecture, network security, assessments) on the client's own template, checked so they read as written by a consultant. Installs itself as a skill for Claude Code, Codex, Gemini CLI, Cursor, Windsurf, Cline and

Minimal, secure Jira MCP server with project-level configuration. 9 tools, ~200 lines, 3 dependencies, zero third-party wrappers. Works with Claude Code, Kiro, Cursor, Windsurf, Codex.

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents