Popular repositories Loading

1. refusal-benchmark refusal-benchmark Public

   519+ harmful prompts to detect how abliterated AI models are

   Python 35 4

2. penclaw penclaw Public

   Forked from openclaw/openclaw

   Your own abliterated personal AI assistant. Any OS. Any Platform. Any prompt, No objections. This is the way. ☬

   TypeScript 15 3

3. skills skills Public

   Red-team your AI agents from any coding IDE. Adversarial security testing skills for Claude Code, Cursor, Codex, and 40+ agents.

   6 1

4. audn-cli audn-cli Public

   CLI for Audn.ai — CI/CD security gate and developer workflows for AI agent red-teaming

   Go 1

5. redclaw redclaw Public

   Forked from openclaw/openclaw

   Your own personal AI assistant. Any OS. Any Platform. Any prompt, No objections. This is the way. ☬

   TypeScript

6. audn-plugin audn-plugin Public

   Audn AI agent behavioural Security QA plugin

   Shell