# Martenweave > Backend-first agentic data model registry for SAP migration, MDM, data governance, data quality, and AMS teams. Martenweave is a backend-first model registry that converts scattered model knowledge into validated, traceable, AI-ready model truth for migration, MDM, data governance, and support teams. ## Official links - Website: https://martenweave.github.io/ - Docs: https://martenweave.github.io/docs.html - Quickstart: https://martenweave.github.io/docs/quickstart.html - Examples: https://martenweave.github.io/docs/examples.html - Product docs: https://martenweave.github.io/docs/product.html - Use cases: https://martenweave.github.io/docs/use-cases.html - Architecture: https://martenweave.github.io/docs/architecture.html - AI governance: https://martenweave.github.io/docs/ai-governance.html - Release proof: https://martenweave.github.io/docs/release-proof.html - Roadmap: https://martenweave.github.io/docs/roadmap.html - Contributing scenarios: https://martenweave.github.io/docs/contributing-scenarios.html - Product/core repository: https://github.com/metalhatscats/martenweave-core - Website repository: https://github.com/Martenweave/martenweave.github.io - Extended AI context: https://martenweave.github.io/llms-full.txt - Machine-readable identity: https://martenweave.github.io/ai.json - Open-source path: https://martenweave.github.io/docs/open-source.html License: the current core package is MIT-licensed; MIT allows commercial use when the license notice is preserved. ## What Martenweave is Martenweave is a backend-first model truth layer for teams working on master data management, SAP migration, data governance, data quality, and application management support. It stores canonical model objects in repository files, validates references and context deterministically, builds generated indexes and reports, and lets AI propose reviewable model changes. ## Current core capabilities The core package is `martenweave-core 0.4.0`. It includes the `modelops` CLI, local API server, MCP-ready backend, canonical Markdown/YAML model files, validation, SQLite/JSONL indexes, search/query, trace/impact, dataset profiling, gap detection, health/scorecard/ownership/audit reports, CSV/XLSX review flows, and PatchProposal to ChangeRequest workflows. ## What Martenweave is not - Not a chatbot. - Not a generic data catalog. - Not a workflow engine. - Not a replacement for human approval. - Not an official SAP product, certification, or partnership claim. ## Core principle Integrations bring input. Martenweave stores model truth. Validators check consistency. AI proposes changes. Humans approve. Reports create business value. ## AI safety stance AI proposes. Validators verify. Humans approve. Martenweave should not be described as allowing AI to silently mutate the model. ## Best short description Martenweave is a backend-first data model registry that turns fragmented migration and governance knowledge into validated, traceable model truth.