Skip to main content

Installation

Initialization

Parameters

Action Types

Response Modes

vt.monitor()

Context manager that wraps your entire agent session.

vt.log_action()

Explicitly log a single agent action.

5-Dimensional Risk Scoring

Every action is scored across five dimensions:

REST API

All endpoints require your API key in the header:

POST /api/check

Pre-execution risk check. Returns decision before action runs.
Response:

PATCH /api/agents//profile

Update an agent’s permission profile from the API.

POST /api/actions

Log a completed agent action.

GET /api/agents

List all registered agents with their permission profiles.

GET /api/alerts

Retrieve active alerts.

Security Policies

Policies let you define rules that automatically block, pause, or allow actions.