romovpa/claudini

Autoresearch for LLM adversarial attacks

241Stars on the repository
2Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

claudini

01

romovpa/claudini

Skill Claude CodeCodex

Run one iteration of the autoresearch loop — study existing attack methods, design a better optimizer, implement it, benchmark it, and commit. Meant to be called repeatedly via /loop.

not rated 241 3mo ago A 42 tokens original Apache-2.0