Runs Claude Code in a sandboxed Docker environment with HTTP proxy filtering
A secure Claude Skills installer with comprehensive malicious operation detection - Skills 安裝器 + 防毒軟體
CConfig - simple and secure Claude API configuration management
Defense-in-depth security skills for Claude Code - CSRF protection, rate limiting, input validation, and more
Security module - CVE fixes, input validation, path security
JSON parse with prototype poisoning protection
A tiny (130B to 205B) and fast utility to randomize unique IDs of fixed length
A tiny (230B) and fast UUID (v4) generator for Node and the browser
simple persistent cookiejar system
Provides functions for detecting if the host environment supports the WebCrypto API
Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.
SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.
Secure, zero-dependency utilities for generating passwords, passphrases, pins, and more
Native binary for Claude Code on linux-x64
Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes
A security-focused rehype plugin that filters URLs based on allowed prefixes
Securely compare two strings, copied from cryptiles
Native CLI binary for @anthropic-ai/claude-agent-sdk on linux-x64
HTTP Server framework
The official TypeScript library for the Anthropic API
SHA1 wrapper for browsers that prefers `window.crypto.subtle`.
Native binary for Claude Code on win32-x64
Native CLI binary for @anthropic-ai/claude-agent-sdk on linux-x64-musl
Sets secure response headers for Next.js.
A Ruby DSL framework for creating Claude Code hooks with composable hook scripts that enable teams to easily implement logging, security checks, and workflow automation.
Scan GitHub Actions workflows for 32 security vulnerabilities. SHA pinning, shell injection, credential exposure, dangerous triggers. Optional AI-powered remediation via Claude. Pure Ruby stdlib.
Rails Active MCP enables secure Rails console access through Model Context Protocol (MCP) for AI agents and development tools like Claude Desktop. Provides safe database querying, model introspection, and code execution with comprehensive safety checks and audit logging. Features include: • Safe Ruby code execution with configurable safety checks • Read-only database query tools with result limiting • Rails model introspection (schema, associations, validations) • Dry-run code analysis for safety validation • Environment-specific configuration presets • Comprehensive audit logging and monitoring • Claude Desktop integration out of the box
Ask questions in plain English, get SQL queries and human-readable answers. Works with any LLM provider (Anthropic Claude, OpenAI, Ollama, or custom). Includes security guardrails: SELECT-only, column blocklists, query timeouts, audit logging.
RcrewAI Rails is a comprehensive Rails engine that brings AI agent orchestration to your Rails applications. Build intelligent AI crews that collaborate to solve complex tasks with full database persistence, background job integration, and a beautiful web dashboard for monitoring and management. Features: • ActiveRecord models for crews, agents, tasks, and executions with full persistence • Rails generators for scaffolding AI crews and agents • ActiveJob integration for asynchronous crew execution (works with any Rails background job adapter) • Web dashboard with real-time monitoring and management interface • Multi-LLM support: OpenAI GPT, Anthropic Claude, Google Gemini, Azure OpenAI, Ollama • Production-ready with logging, error handling, and security controls • Human-in-the-loop workflows with approval mechanisms • Tool ecosystem: web search, file operations, SQL, email, code execution
RCrewAI is a powerful Ruby framework for creating autonomous AI agent crews that collaborate to solve complex tasks. Build intelligent workflows with reasoning agents, tool usage, memory systems, and human oversight. Key Features: • Multi-Agent Orchestration: Create crews of specialized AI agents that work together • Multi-LLM Support: OpenAI GPT-4, Anthropic Claude, Google Gemini, Azure OpenAI, Ollama • Rich Tool Ecosystem: Web search, file operations, SQL databases, email, code execution, PDF processing • Agent Memory: Short-term and long-term memory for learning from past executions • Human-in-the-Loop: Interactive approval workflows and collaborative decision making • Advanced Task Management: Dependencies, retries, async execution, and context sharing • Hierarchical Teams: Manager agents that coordinate and delegate to specialist agents • Production Ready: Security controls, error handling, comprehensive logging, and monitoring • Ruby-First Design: Built specifically for Ruby developers with idiomatic patterns • CLI Tools: Command-line interface for creating and managing AI crews