A living map of the AI agent security ecosystem.
-
Updated
Jun 12, 2026
A living map of the AI agent security ecosystem.
A Serverless Security Library for Developers. Regain Control Over Your AWS Lambda & Google Cloud Functions Runtimes.
🛡️ Proactive Runtime Injection Shield & Monitor for OpenClaw — injection scanning, tool execution guard, DLP, and file integrity monitoring
Runtime integrity guard: detect and block Linux page cache tampering (Copy Fail, Dirty Pipe, Dirty Frag) via O_DIRECT + fanotify. Includes 7 host-side exploitation PoCs.
Dhi - Runtime Intelligence & Protection System. Sanskrit: Intellect | Perception. Kernel-space eBPF security monitoring for AI agents.
🛡️ The CrowdStrike for AI Agents — Runtime protection, threat detection & security monitoring for LLM agents. Supports LangChain, CrewAI, AutoGen, OpenAI. Python • JS • Rust • Go • Ruby • .NET
Security Research Project: A B.Tech minor project built upon an Android calculator application, extended to implement and evaluate security mechanisms such as anti-debugging, root and emulator detection, runtime protection, and code obfuscation. The work focuses on analyzing Android app resilience against tampering and reverse engineering.
Control plane for enterprise AI security: inline runtime guardrails, automated red teaming with auto-remediation, AI asset posture (AI-SPM), and compliance governance. Python control plane + Go inline agent.
Runtime protection for AI coding agents. Intercepts tool calls, scores them against the task, blocks prompt injection attacks before execution.
Simple low-level Android antivirus
A clone of an opensource project where I was a major contributor for Reblaze in 2020. See also the talk https://youtu.be/6_8CkDWz3XQ that was inspired by this work.
Security scanner and runtime protection for MCP (Model Context Protocol) servers
Impart Security is a runtime security platform that unifies WAF, API security, and AI/LLM/agent/MCP protection on one inline enforcement engine. It analyzes the full request/response flow — headers, parameters, query strings, and bodies — models API behavior with machine learning, detects anomalies from a learned baseline, and takes inline…
Raspire Inc. (RASPIRE) is a mobile application security company offering AI-powered, no-code runtime application self-protection for Android and iOS apps. Its SHIELD / XTD platform applies configuration-driven defenses that protect every release from code tampering, reverse engineering, hooking/injection, MITM interception, rooted or jailbroken…
Technical documentation and security resources for Metin2 private servers.
Runtime prompt injection scanner for Node.js. Trusted users, attack notifications, Express middleware. Zero deps, < 1ms.
Explore AI security tools, papers, and frameworks for testing ML, LLM, and agentic AI systems
Noname Security (acquired by Akamai in 2024) is an API security platform that provides complete API discovery, posture management, runtime protection, and active testing capabilities.
Akamai API Security (formerly Noname Security) provides comprehensive API discovery, posture management, and threat protection for organizations across cloud, on-premises, and hybrid environments.
C++ game usermode anti-cheat
Add a description, image, and links to the runtime-protection topic page so that developers can more easily learn about it.
To associate your repository with the runtime-protection topic, visit your repo's landing page and select "manage topics."