RestaRules – A robots.txt for how AI agents interact with restaurants

RestaRules is an open standard that lets restaurants publish machine-readable conduct rules for AI agents. Any agent — voice, booking, concierge — checks a /.well-known/agent-venue-rules.json file before acting. The rules cover things like: must the AI disclose it's not human? Which channels are allowed (phone, web, SMS)? What's the party size limit before a human gets involved? Are deposits required? What are the retry limits? Think of it as robots.txt, but instead of "don't crawl this page," it's "don't book a table for 12 without calling the host stand first." Why now: AI voice agents are already calling restaurants. NY and Philadelphia passed anti-bot reservation laws. The EU AI Act (August 2026) requires AI-to-human disclosure. Restaurants have zero standardized way to set boundaries. The repo includes a v0.2 JSON Schema, a validation SDK, a CLI checker, a reference agent, and a browser voice demo where you can hear an agent fetch live rules and obey them. Live demo: https://selfradiance.github.io/restarules/demo/voice/ Live rules file: https://selfradiance.github.io/restarules/.well-known/agent-... Built solo with no prior coding experience using AI coding agents (Claude Code). Happy to answer questions about the standard or the process.