#agent-security

DataFog: PII Firewall for AI Agents

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls...

Gensee Crate: AI Agent Runtime Safety

Runtime safety for AI coding agents with real-time enforcement, system-event monitoring, and long-horizon provenance. Supports Claude Code,...

Repo Forensics

Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.

Asamm

Agentic SAMM - An OWASP SAMM Extension for AI-Driven Development

Honeymcp

Open-source honeypot for MCP (Model Context Protocol) servers. Collects threat intel on attacks against the AI agent ecosystem.

Secure Claude Code

Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltr...

Aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking...

Agentgate

Collateralized execution engine for AI agents: bond-and-slash accountability with Ed25519 identities, bounded exposure, and progressive trus...

AgentArmor

🛡️ Open-source AI security scanner & LLM red-teaming platform. Test LLM APIs, chatbots, agents, MCP servers & RAG for prompt injection, jail...

SecureContext

Persistent memory + security layer for Claude Code (MCP plugin). Agents remember your project across sessions (~87% fewer context tokens), e...

AgentShield

Security layer for AI agents: real-time interception of pip/npm/cargo/gem/go installs via Hermes & OpenClaw plugins, Claude Code/Codex hooks...

Mcpsafetywarden

MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP ser...