Hacker News · AI·· 29 min agoAI score58
Project Chaperone: a rule-enforcing harness that audits AI agent workflows before they run
AI Agentic harness with explicit risk analysis
AI summary
Applied Ingenuity released Project Chaperone, an open-source harness that lets agentic AI call tools while enforcing high-level policies such as no personal data leaving the network. A startup audit checks every route of all workflows for rule violations and asks a human to approve scoped exceptions, which are recorded per project; enforcement at runtime then relies on data labels like UNTRUSTED and PERSONAL plus module properties such as OUTPUT and LEAVES_NETWORK. The repo ships five shared default rules and four examples, including deliveries, share_notes, ask_my_mail and safe_rag, and an LLM is optional.
Source:Hacker News · AI · github.com