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.

If you are deploying your first agent, start with Getting Started. If you are evaluating the governance model or writing a Mandrel Spec, move to Architecture and The Mandrel Spec. If you are integrating tooling or operating the mesh, go directly to Reference.

Key Sections

• White Papers: Technical deep-dives and security framework alignments, including our direct enforcement model for Google’s SAIF.
• 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.
• Deployment Variants: Universal governance across Kubernetes, Serverless, and Managed Agent Platforms.
• Governance Maturity: Evolving from Shadow AI to a hardened, optimized Agentic Mesh.
• Established Ecosystems: Gradual mesh adoption strategy for existing agent environments.
• The Mandrel Spec: The declarative governance contract — schema reference, identity, orchestration, and token budgets.
• Roadmap: The future vision for the Mandrel open source ecosystem.
• Reference: CLI commands, diagnostic codes, Collet enforcement layers, and platform resource schemas.