Story · arXiv
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents (arXiv)
paper · Story page
A local-first runtime that separates what the model proposes from what the host authorizes and executes, with permissions, memory, replay, sub-agents and traces as explicit layers. The paper claims no formal safety guarantees; the point is an inspectable architecture.
In plain words
- Researchers presented Agentao, software for controlling artificial intelligence systems that use tools and change information on a user's computer.
- The artificial intelligence system proposes an action, but the computer's controlling software decides whether to allow and perform it.
- Separate layers record permissions, stored information, repeated runs, added tools, delegated helpers, and communication with other systems.
- Its records let people inspect what happened and reproduce earlier actions.
- The design could help people oversee these systems, but the researchers do not claim it guarantees safety.
Appeared in
- Deno's Claw Patrol treats agents as untrusted software, and full history beats compaction
Aug 18, 2026 · in the sections
Subscribe
Get the brief in your inbox
Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.
- Weekdays at 8:45am IST, one lead story and 6 to 9 items.
- Sundays, an argued synthesis rather than a recap.
- One click to leave, and quiet days say so in the subject line.