Search

Memory poisoning detection primitives for AI agents — pure pattern matchers (RAG trust, agent-role imperatives, tool-output poisoning, capability expansion, injection fingerprints) + opt-in Agentic Control Center event bus. Extracted from chitta-guard.

AgentMesh trust layer integration for LangChain - cryptographic identity and trust-gated tool execution

The testing framework dedicated to ML models, from tabular to LLMs

An Execution Isolation Architecture for LLM-Based Agentic Systems

AI Native Agent Skill 安全审计工具 —— LLM 驱动的多阶段代码审计与漏洞复审流水线

AI-operated company. Building agent-friend: universal tool adapter for AI agents. @tool → OpenAI, Claude, Gemini, MCP. Live 24/7 on Twitch.

Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)

Omega Walls v1 safety layer for RAG/agents

Agentic LLM injection benchmark — VisorCorpus payload delivery, VisorSD target discovery, HIT/MISS matrix per vector

A zero-trust SDK for anonymizing PII locally before sending prompts to LLMs and seamlessly rehydrating the response.

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.

AI Agent Tool for Penetration Testing and Network Forensics

ML classifier add-on for Agent Armor. Downloads and runs a DeBERTa-v3-small ONNX model for agent trap detection.

ISO 27001 ISMS template designed to be instantiated and maintained by an LLM Agent

Architectural decision records on accountability distribution in autonomous AI agents — 10 ADRs + 4 Business AI Quadrants + Phase Separation axis. Harness-neutral practice library extracted from contemplative-agent. DOI on Zenodo.

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.

Browser automation for AI agents - integrates agent-browser with cognition swarms

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

Open-source reverse engineering lab: 197-article knowledge base + MCP tools + CTF/APK/PE automation toolchain. Agent-native.

Unified AI execution runtime / framework & sandbox for coding agents across CLI, VS Code, terminal, and web surfaces. Rust frame work, programmable capabilites.