OpenAPPA

About OpenAPPA

An information-flow policy engine for LLM agents.

In the maker’s words

Hi Hacker News! Matvey, one of the authors, is here. While building enterprise agents, we ran into a problem: the more tools you connect to the AI, the higher the chance it will run out of control and leak sensitive data. Guardrails, in theory, should prevent this, but the situation is worrying: - Non-deterministic guardrails (LLM as a judge, auto modes, etc.) are vulnerable to prompt injections, or they lack knowledge of the data, making them inefficient (~10% data leaks on our benchmarks). - Existing deterministic guardrails (Cedar, OPA, FIDES, Dogwood) require massive case-specific IF-ELSE-like policies and break agents (~59% utility loss on our benchmarks). We did something differently. We’ve taken the best of existing deterministic guardrails and built a policy language that is data-specific, not use-case specific. It lets you scale agents without updating a policy. On top of that, …

Where people found it

• Hacker NewsShow HN: OpenAPPA – open-source deterministic guardrails that don't break agents25 points12 comments5 days ago