marmot
Prevents AI agents from operating on stale or incorrect data by centralizing metadata governance.
The open-source context layer for your AI. Catalog your tables, topics, queues and APIs then expose real metadata to your AI agents.
- Ask Claude to query your database by exposing table schemas and metadata through Marmot.
- Generate accurate API responses by cataloging all available endpoints and their parameters.
- Automate data discovery by letting Claude understand your entire data infrastructure.
Prevents AI agents from operating on stale or incorrect data by centralizing metadata governance. Reduces hallucination risk and improves decision accuracy in data-driven workflows.
Data engineering teams building AI-powered analytics platforms needing reliable semantic context.
https://github.com/marmotdata/marmot
By marmotdata
How to Get It
claude plugins install marmotdata/marmot
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Query my database by exposing table schemas and metadata through Marmot
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Show HN: Marmot – Single-binary data catalog (no Kafka, no Elasticsearch) — Hacker News · 103 pts
- Show HN: Marmot, context layer for agents and humans — Hacker News · 17 pts
- Show HN: Marmot – Simple data catalog with powerful search and lineage — Hacker News · 2 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 612 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 612 GitHub stars; contributors unknown; last commit 0d ago; license MIT.