anthropics/mythos-5-incident-transcript

A dataset containing Office 365 Unified Audit Logs for security research and detection

LLM agent solving traces, leaderboards, and benchmark results across security CTF and hacking platforms

Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.

Local forensic scanner that extracts credentials from AI tool conversation history. For authorized red team and DLP use only.

ATLAS tactics, techniques, and case studies data

Transcript analysis for long-horizon agent evaluations

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas and agent harnesses powering today's AI products. Captured with OrcaReplay.