Comment by ramoz

After creating the feature request for Claude Code hooks[1] a few months back, Cupcake is nearly ready for release.

Cupcake is a governance/policy-enforcement layer for agents. Its innovation is binding OPA/rego to agent runtimes (via hooks).

I do not believe we will every strictly rely on "better" models in the wild without deterministic guarantees or ways for enterprises to factor in their own alignment - system prompts dont cut it.

https://github.com/eqtylab/cupcake

Stay tuned for the formal release here in a couple of weeks.

[1] https://github.com/anthropics/claude-code/issues/712

Cupcake GitHub: https://github.com/eqtylab/cupcake