The AI that refuses to think for you. Open-source anti-deskilling framework implementing human-AI collaboration protocols from the Cabitza lab (Milano-Bicocca). Four modes: Forge, Anvil, Crucible, Executor.

Still exercising judgment, or just accepting what the AI says? A local, private tracker of cognitive offloading and AI over-reliance, from your own transcripts. A personal proxy of the Offloading Score. Aggregates-only. Offload the work, never the judgment.

Agent Skill that quizzes you on its own answers — one multiple-choice question after each substantive reply, graded and explained. Ambient retrieval practice against AI deskilling. Instruction-only: no scripts, no network, no data sent. MIT.