
caos-os
Customer Assurance Operating System. Answer the security questionnaires your customers send you, once.

Customer Assurance Operating System. Answer the security questionnaires your customers send you, once.

Research code for red-teaming AI auto-mode monitors, including simulation evals, fuzzing, and monitor implementations for Claude Code and Codex…

Defensive framework that maintains a safety-focused shadow memory to detect and block prompt-injection and long-horizon threats against LLM agents…

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

Proof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…

0-day malware detection for binaries, source & scripts (that doesn't suck)

First iteration of ML based Feedback WAF

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

Restructured and Collaborated SIEM and CVSS Infrastructure. Presented at Blackhat Asia Arsenal 2020.

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks. Red Team AI Benchmark is a CLI model-evaluation benchmark. It…

This tool parses log data and allows to define analysis pipelines for anomaly detection. It was designed to run the analysis with limited resources…

Multi-agent automated context management for long horizon tasks in local AI Agents

The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers…

Stalk your Friends. Find their Instagram, FB and Twitter Profiles using Image Recognition and Reverse Image Search.

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞