Agent Aware Architecture: an open spec to make sites walkable for AI agents
sierracatalina · x · 2026-10-03
sierracatalina open-sourced agent-aware-starter, proposing Agent Aware Architecture (AAA): a machine-readable handshake so agents read a small set of well-known files instead of inferring intent from the DOM. "Google ranks pages; agents rank paths — make yours walkable."
The handshake fetches /.well-known/llms.txt, agents., and ai-instructions., then honors actionroot: either call only mapped actions or, if "none", open documented pages. The spec covers a Settings surface, safety guardrails and confirmations, ownership boundaries, with JSON Schemas and fixtures included.
More from coding & agent
- Vibe coding is driving major projects to rewrite in Rust over cheaper vCPU costs — evilsocket · 2026-10-03
- Users slam Dots: permission blocks, dead sub-agents, and "unlimited Astra" quietly burning local Codex limits — brandon_galang · 2026-10-03
- The foo[count:-count] gotcha: -0 silently empties your array slice — theshawwn · 2026-10-03
- Dev open-sources an approval-queue tool that stops AI agents from sending anything until you sign off — paulofilip3 · 2026-10-03
- Princeton-backed Choir open-sources a protocol for multi-agent autoformalization on GitHub — burny_tech · 2026-10-03
- Running 256k-context open models on 2x RTX 3090 for months: a home server LLM retrospective — knighty1981 · 2026-10-03