Official SDK for the AgentShield security protocol — real-time smart contract security for autonomous AI agents
Security auditor for AI agent configurations. Scans Claude Code setups for vulnerabilities, misconfigs, and injection risks.
Complete collection of battle-tested Claude Code configs — agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use by an Anthropic hackathon winner
Instant file protection for AI agent operations - hardlink-based zero-copy backup system
SOTA AI agent security SDK. F1 1.000 on BIPIA/HackAPrompt/MCPTox/Multilingual benchmarks. 400+ exports, 100+ modules. Zero dependencies, runs locally.
Runtime security middleware for LLM agents — prompt injection, tool misuse, and memory poisoning defense
Checkpoint SDK — base library for AI agent detection and analysis (formerly @kya-os/agentshield)
AgentShield SDK for AI agent safety and guardrails
MCP server for AgentShield — detect prompt injection, jailbreak, and social-engineering attempts in any text before your agent processes it.
Multi-engine AI agent security scanner — one scan, four engines, one report
AgentShield core policy evaluation engine — deterministic runtime governance for AI agents
TypeScript type definitions for AgentShield Beacon
Security scanner for AI Agents and MCP Servers — 10 scanners for prompt injection, supply chain poisoning, secret leaks, and misconfigs
AgentShield SDK — Scan content for prompt injection before your AI agent acts on it
AgentShield MCP server — real-time smart contract security for AI agents. Verify contracts for honeypots, rug pulls, and risks via x402 micropayments.
AgentShield — Deterministic Runtime Policy Engine for AI Agents. Intercept, evaluate, and govern every tool call.
The TypeScript MCP framework with identity features built-in
Source of truth for Checkpoint detection rules. Do not maintain rule tables outside this package — see CONTRIBUTING.md § 'Rules SSOT'.
Firewall and audit logger for MCP agent-to-tool connections — intercept, log, and enforce policies on every tool call your AI agents make
Security review and compliance audit extension for Pi coding agents
Array#isArray for older browsers
Complete collection of Factory Droid configs — droids, skills, hooks, rules, and command shims for modern engineering workflows.
CLI arguments parser. Native port of python's argparse.
Get the command from a shebang