SWT3 AI Witness
io.tenova/swt3-witness
Cryptographic AI governance + audit. 18 tools, 28 frameworks. EU AI Act, NIST, OWASP, CMMC, SR 11-7
Install surfaces
How SWT3 AI Witness runs, per the official MCP registry entry.
- npm
@tenova/[email protected]
Governed execution
How KLA gates calls to SWT3 AI Witness once it is connected.
A published policy defines which SWT3 AI Witness actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agent frameworks and model providers you already run. See integrations.