Repository History
69 repositories tagged with ai-agents
Anthropic Cybersecurity Skills: 754 Structured Skills for AI Agents
This repository offers the largest open-source library of 754 structured cybersecurity skills designed for AI agents. It maps these skills across five industry frameworks, including MITRE ATT&CK and NIST CSF 2.0, enabling AI agents to perform expert-level security analysis and operations. The project aims to empower AI with practitioner playbooks to address the global cybersecurity workforce gap.
APM: Agent Package Manager for AI Agents
APM, the Agent Package Manager, is an open-source, community-driven dependency manager designed specifically for AI agents. It aims to standardize and streamline the configuration of AI coding agents, making their context portable, secure, and reproducible across different environments. This tool addresses the challenge of manually setting up agent dependencies by providing a manifest-driven approach, similar to traditional package managers like npm or pip.
Oh-My-ClaudeCode: Teams-First Multi-Agent Orchestration for Claude Code
Oh-My-ClaudeCode is a powerful GitHub repository that provides teams-first multi-agent orchestration for Claude Code, enhancing its capabilities with zero learning curve. It enables developers to build, refactor, and verify code efficiently through intelligent automation and parallel execution. This tool aims to supercharge your Claude Code experience, making complex development tasks simpler and more cost-effective.
claude-mem: Persistent Context Across Sessions for AI Agents
claude-mem is an innovative GitHub repository designed to provide persistent context across sessions for various AI agents. It intelligently captures agent activities, compresses them using AI, and injects relevant information into future interactions. This powerful tool supports a wide range of AI platforms, including Claude Code, OpenClaw, Gemini, and Copilot.
MCPJungle: Self-Hosted MCP Gateway for AI Agents and Tool Management
MCPJungle is an open-source, self-hosted Model Context Protocol (MCP) Gateway designed for managing AI agents and their tool-calling capabilities. It allows developers and organizations to centralize the registration, discovery, and consumption of MCP servers and their tools, enhancing security and control over AI agent interactions.
brightdata-mcp: Empowering AI with Real-time Web Access and Data Scraping
The brightdata-mcp is a powerful Model Context Protocol (MCP) server developed by Bright Data, designed to give AI agents real-time web access. It provides an all-in-one solution for seamless public web interaction, ensuring Large Language Models (LLMs) can access live information without encountering blocks or CAPTCHAs. This open-source project offers robust web scraping, browser automation, and data extraction capabilities.
mcp-agent: Build Effective AI Agents with Model Context Protocol in Python
mcp-agent is a powerful Python framework designed to help developers build effective AI agents using the Model Context Protocol (MCP) and simple, composable workflow patterns. It fully implements MCP, providing robust support for agent lifecycle management and integrating patterns from Anthropic's 'Building Effective Agents'. This framework simplifies the creation of durable, production-ready agent applications.
Browserable: Open Source Browser Automation for AI Agents
Browserable is an open-source and self-hostable library designed to empower AI agents with advanced browser automation capabilities. It enables agents to navigate websites, fill out forms, click buttons, and extract information efficiently. With a strong performance on Web Voyager benchmarks, Browserable provides a robust foundation for building intelligent AI-driven web interactions.
HexStrike AI MCP Agents: AI-Powered Cybersecurity Automation Platform
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents, such as Claude, GPT, and Copilot, autonomously run over 150 cybersecurity tools. It enables automated pentesting, vulnerability discovery, bug bounty automation, and security research. This platform seamlessly bridges large language models (LLMs) with real-world offensive security capabilities.