#policy

Cross-agent permission policy for AI coding agents. MCP sync daemon, CLI, codecs, and evaluator. One .agents/permissions.json for every agent.

The pause is where tools break: approval out of band, token minted at execution, arguments bound to what a human saw, spent once, sealed in a hash-chained receipt.

Neutral self-hosted registry and toolkit for Agentic Resource Discovery.

Autonomous agents with receipts.

Global Laboratory for AI Progress and Governance: Open Systems — The open multilateral AI platform for the Americas

Audit trail and traceability for AI agents. See what every coding agent did, with opt-in human approval and signed certify.

Stop an AI agent before it spends your money. Local kill switch, spend caps, and approval gates for tool calls.

A policy hook for Claude Code

Fail-closed control plane for agentic SDLC. Portable skills, evidence ladder, SPIFFE/WIMSE identity. Intent is not a grant.