Instant file protection for AI agent operations - hardlink-based zero-copy backup system
AgentShield SDK for AI agent safety and guardrails
TypeScript type definitions for AgentShield Beacon
Security auditor for AI agent configurations. Scans Claude Code setups for vulnerabilities, misconfigs, and injection risks.
MCP server for AgentShield — detect prompt injection, jailbreak, and social-engineering attempts in any text before your agent processes it.
Checkpoint shared types and schemas (formerly @kya-os/agentshield-shared)
Canonical consent page types, styles, and utilities for MCP-I and AgentShield
AgentShield SDK — Scan content for prompt injection before your AI agent acts on it
Checkpoint SDK — base library for AI agent detection and analysis (formerly @kya-os/agentshield)
AgentShield core policy evaluation engine — deterministic runtime governance for AI agents
Checkpoint Next.js middleware for AI agent detection (formerly @kya-os/agentshield-nextjs)
AgentShield MCP server — real-time smart contract security for AI agents. Verify contracts for honeypots, rug pulls, and risks via x402 micropayments.
Official SDK for the AgentShield security protocol — real-time smart contract security for autonomous AI agents
Checkpoint WASM runtime for AI agent detection across all environments (formerly @kya-os/agentshield-wasm-runtime)
AgentShield LangChain integration — callback handler for AI agent policy governance
SOTA AI agent security SDK. F1 1.000 on BIPIA/HackAPrompt/MCPTox/Multilingual benchmarks. 400+ exports, 100+ modules. Zero dependencies, runs locally.
AgentShield — Deterministic Runtime Policy Engine for AI Agents. Intercept, evaluate, and govern every tool call.
TypeScript client for the AumOS AgentShield defense layer — threat detection, input/output scanning, and tool-call validation
AgentShield real-time security evaluation plugin for OpenClaw. Intercepts tool calls before execution and evaluates them against Sigma detection rules.
Core policy gateway and signature verification for AgentShield
HTTP gateway service for AgentShield
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
Express middleware for MCP-I proof verification and AI agent authorization using AgentShield Bouncer
CLI for AgentShield
AI Agent Egress Firewall - Default-deny egress control for AI agents
Security scanner for AI agent extensions — offline-first, multi-framework, SARIF output
Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents
No description provided.
No description provided.
No description provided.