Launching today
Watchtower

Watchtower

Task-scoped runtime security for AI agents

0 followers

Watchtower is an open-source experiment in task-scoped authority for autonomous AI agents. Define an agent's task and capabilities, generate an authority boundary, then test actions as ALLOW, REVIEW, or BLOCK. The MVP includes a Security Lab and an audit trail. What's different: we're exploring whether an agent's authority can be derived from its current task and eventually enforced at the runtime layer.

Watchtower makers

Here are the founders, developers, designers and product people who worked on Watchtower