Documentation

Welcome to the Mandrel Project documentation. Here you will find conceptual guides, architecture deep-dives, and technical references for our zero-trust agent governance ecosystem.

Role-Based Pathways

Select a reading path based on your role and operational focus:

• Agent Developers:
  Start with Getting Started to build your first spec → explore the Core Schema → check the Mandrel CLI Reference and Diagnostic Codes.
• Platform & Security Engineers:
  Review the Architecture → configure Identity & Security → deploy the Metrology Lab and Egress Governance.
• Enterprise Evaluators & CISOs:
  Read the SAIF Alignment White Paper → assess Governance Maturity → follow the Workload Maturity Guide.

Documentation Directory

• What’s a Mandrel?: Why precision governance borrows a machinist’s vocabulary.
• Getting Started: Deploy your first governed agent in four steps — spec, validate, generate, deploy.
• Architecture: How the Collet, Gantry, and Metrology Lab interact and where governance is enforced.
• Workload Maturity Guide: Actionable checklist for advancing workloads from Tier 1 (Sandbox) to Tier 4 (Autonomous).
• Deployment Variants: Universal governance across Kubernetes, Serverless, and Managed Agent Platforms.
• Egress Governance: Outbound tool proxying, Envoy transparent interception, and Collet fallback modes.
• The Mandrel Spec: The declarative governance contract — schema reference, identity, orchestration, and token budgets.
• White Papers: Security framework alignments, including Google’s SAIF, governance maturity, and shadow AI discovery.
• Reference: CLI toolchain, Collet proxy layers, Metrology Lab contracts, Kong integration, and Diagnostic Codes.
• Open Source Roadmap: Long-term vision for the open-source governance core.