Discover any data asset in seconds. Then let your AI do the same.
How to install marmot?
marmotdata/marmot
$git clone https://github.com/marmotdata/marmotInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install marmot by running `git clone https://github.com/marmotdata/marmot`, then use it for the current task and follow its documentation at https://github.com/marmotdata/marmot.
README.md
| 1 | <div align="center"> |
| 2 | <img src="./marmot.svg" width="180"> |
| 3 | |
| 4 | # Marmot |
| 5 | |
| 6 | **Discover any data asset in seconds. Then let your AI do the same.** |
| 7 | |
| 8 | _The open-source context layer for your AI. Catalog your tables, topics, queues and APIs then expose real metadata to your AI agents._ |
| 9 | |
| 10 | [Documentation](https://marmotdata.io/docs/introduction) • [Live Demo](https://demo.marmotdata.io) • [Deploy](https://marmotdata.io/docs/Deploy) • [Community](https://discord.gg/TWCk7hVFN4) |
| 11 | |
| 12 | </div> |
| 13 | |
| 14 | ## What is Marmot? |
| 15 | |
| 16 | Marmot is an **open-source data catalog** for teams who want powerful data discovery without enterprise complexity. Catalog every data asset, enrich it with the context that matters and make it accessible to your team and your AI tools. |
| 17 | |
| 18 | Unlike traditional catalogs that require extensive infrastructure and configuration, Marmot ships as a **single binary** with an intuitive UI, making it easy to deploy and start cataloging in minutes. |
| 19 | |
| 20 | <div align="center"> |
| 21 | |
| 22 | <a href="https://www.youtube.com/watch?v=_JBcQGj_bFU"> |
| 23 | <img src="https://img.youtube.com/vi/_JBcQGj_bFU/maxresdefault.jpg" alt="Watch the Marmot demo on YouTube" width="480"> |
| 24 | </a> |
| 25 | |
| 26 | <p><a href="https://www.youtube.com/watch?v=_JBcQGj_bFU">▶ Watch the 2-minute demo</a></p> |
| 27 | |
| 28 | </div> |
| 29 | |
| 30 | ## Features |
| 31 | |
| 32 | - **Search everything**: Find any data asset in seconds with full-text search plus structured queries, boolean logic and metadata filters. |
| 33 | - **Interactive lineage**: Trace data flows from source to destination and analyse impact before making changes. |
| 34 | - **Metadata-first**: Store rich metadata for any asset type, from tables and topics to APIs and dashboards. |
| 35 | - **Team collaboration**: Assign ownership, document business context and maintain shared glossaries. |
| 36 | - **AI-ready**: Expose certified context through MCP, the API and the UI. |
| 37 | |
| 38 | <div align="center"> |
| 39 | <img alt="Marmot context layer showing plugins, integrations and AI agents" src="./web/docs/static/img/graph.png" width="900"> |
| 40 | </div> |
| 41 | |
| 42 | ## Deploy |
| 43 | |
| 44 | **New to Marmot?** Follow the [Deploy](https://marmotdata.io/docs/Deploy) documentation for a guided setup, or try the [live demo](https://demo.marmotdata.io). |
| 45 | |
| 46 | ## Development |
| 47 | |
| 48 | See [Local Development](https://marmotdata.io/docs/Develop/local-development) for how to get started developing locally. |
| 49 | |
| 50 | ## Community |
| 51 | |
| 52 | Join our [Discord community](https://discord.gg/TWCk7hVFN4) for help, feedback and updates on new features. |
| 53 | |
| 54 | ## Contributing |
| 55 | |
| 56 | All types of contributions are encouraged and valued! |
| 57 | |
| 58 | - Report bugs or suggest features via [GitHub Issues](https://github.com/your-org/marmot/issues) |
| 59 | - Improve documentation |
| 60 | - Build new plugins for data sources |
| 61 | |
| 62 | Before contributing, please check out the [Contributing Guide](CONTRIBUTING.md). |
| 63 | |
| 64 | |
| 65 | |
| 66 | ## FAQ |
| 67 | |
| 68 | ### What is Marmot? |
| 69 | |
| 70 | Marmot is an **open-source data catalog** for teams who want powerful data discovery without enterprise complexity. It catalogs every data asset (tables, topics, queues, APIs), enriches it with context, and makes it accessible to both your team and AI tools. Unlike traditional catalogs requiring extensive infrastructure, Marmot ships as a **single binary** with an intuitive UI. |
| 71 | |
| 72 | ### Why Use Marmot? |
| 73 | |
| 74 | | Feature | Benefit | |
| 75 | |---------|---------| |
| 76 | | **Search Everything** | Find any data asset in seconds with full-text search, structured queries, boolean logic, and metadata filters | |
| 77 | | **Interactive Lineage** | Trace data flows from source to destination, analyze impact before making changes | |
| 78 | | **Metadata-First** | Store rich metadata for any asset type (tables, topics, APIs, dashboards) | |
| 79 | | **Team Collaboration** | Assign ownership, document business context, maintain shared glossaries | |
| 80 | | **AI-Ready** | Expose certified context through MCP, API, and UI | |
| 81 | | **Single Binary** | No complex infrastructure required, deploy in minutes | |
| 82 | |
| 83 | ### How Does Marmot Integrate with AI Agents? |
| 84 | |
| 85 | Marmot exposes certified context through **MCP (Model Context Protocol)**, enabling AI agents to query real metadata about your data assets. This allows AI tools to understand your |
Related
6 picksType
- dbt-mcpA MCP (Model Context Protocol) server for interacting with dbt resources.Jul 2026
- mcp-server-chartA Model Context Protocol server for generating charts using AntV.May 2026
- jupyter-mcp-server🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.Jul 2026
- tableau-mcpHelping agents see and understand data.Jul 2026
- oxylabs-mcpFetch and process content from specified URLs & sources using the Oxylabs Web Scraper API.Jun 2026
- aix-dbAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。Jun 2026
