Search

Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests.

Aegis Invariant Kernel Middleware & Tool Wrapper for Vercel AI SDK (Core / AI)

Runtime firewall for AI agents - blocks catastrophic tool calls and self-heals the run.

AI Cybersecurity intelligence gathering streamlit web app using Cohere's Command A model + Tool Use Agent that utilizes Shodan, VirusTotal, AbuseIPDB, and CVE databases for a comprehensive threat assessment for Websites, CVE's, IP addresses, and Software.

MCP server for AI-driven security pipelines

Vaultak runtime security callback handler for LangChain agents

Security guardrails for AI agents - prompt injection detection & credential protection

AI-powered security scanner with 15 scan phases, 10 specialist agents, container/IaC/DAST/taint analysis, and AI-assisted remediation.

A harness that lets any strong coding model work like a security researcher — narrow scoping, adversarial cross-model review, capability-split tools, parallel hunt + dedupe.

Drop-in prompt injection defense for LLM apps and AI agents — detect, block, and audit injection attacks in real time

Soter is a safety layer for AI chatbots, agents, RAG systems, and LLM applications.

Open detection rules for AI agent threats. Like Sigma, but for prompt injection, tool poisoning, and agent manipulation.

A zero-trust encrypted transport layer for AI agents and tools, with AES-GCM encryption, HMAC signing, and identity-aware JSON-RPC messaging.

Michael Adams — security specialist agent for Claude Code with persistent memory, STRIDE threat modeling, and OWASP framework mappings.

Agent Security Evaluation Kit — score agent code and refuse unsafe tools, with receipts, AST checks, and live-trace adapters.

🦞 Security-first starter template for OpenClaw agents — 4-layer protection against prompt injection, unauthorized access, and tool misuse. Docker-ready.

AI got hands. This is the leash. Policy, audit, kill switch for any AI agent with access to your accounts.

AI Agent Security Platform SDK - Secure your LangChain agents with policy enforcement

Security moat for AI agents. Runtime protection against prompt injection, tool misuse, and data exfiltration.

Agentic AI runtime security platform — detects, correlates, and interrupts the Lethal Trifecta attack pattern across all agentic AI systems.