Building a model-agnostic enforcement layer for AI systems. Invariants that govern model outputs.
Popular repositories Loading
-
agent-buccet
agent-buccet PublicAgents cannot act outside the laws you set. The brakes & bodyguard for AI agents. They can propose. They never authorize. Alignment + enforcement.
TypeScript 2
-
-
ai-failure-periodic-table
ai-failure-periodic-table PublicA Periodic Table attempting to organize infinite AI failure into 7 dimensions and 343 distinct classes. Try to find something that is not here. Meant to be a community challenge to build the Brakes…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
