# Superlibrary

> Superlibrary is the memory of the stack. It keeps artifacts (uploaded or agent-linked files and folders, versioned) and work records (Superpipeline cards), each labelled with an outcome: approved, completed, in-progress, superseded, rejected, failed or abandoned. Uploads pass path rules, size limits and a secret scan. Search fuses full-text and vector results and ranks by outcome, within what the caller may see. People use the web app and the suli CLI; agents use an MCP server with three read-only tools; products use the HTTP API and an embeddable viewer. It runs on Cloudflare Workers, signs in through the SuperJackfruit account service, and is MIT licensed.

## Documentation Sets

- [Abridged documentation](https://docs.superlibrary.dev/llms-small.txt): a compact version of the documentation for Superlibrary, with non-essential content removed
- [Complete documentation](https://docs.superlibrary.dev/llms-full.txt): the full documentation for Superlibrary

## Notes

- The complete documentation includes all content from the official documentation
- The content is automatically generated from the same source as the official documentation

## Optional

- [Superlibrary](https://superlibrary.dev): The product site.
- [Source](https://github.com/SuperJackfruitLabs/superlibrary): The Superlibrary repository on GitHub.