> For the complete documentation index, see [llms.txt](https://neutron-4.gitbook.io/neutron-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://neutron-4.gitbook.io/neutron-docs/getting-started/seeds-the-foundation-of-myneutron.md). # Seeds: The Foundation of myNeutron Everything in myNeutron starts with a **Seed.** > **A Seed is a Saved Piece of Knowledge.** It captures what you save, upload, or sync and turns it into structured context your AI can use. Each Seed acts like a memory cell for your personal AI brain.\ Together, they form your permanent, searchable memory inside myNeutron. *** #### A Seed Could Be * A webpage you saved * A paragraph you highlighted * A PDF, note, or image you uploaded * An email or file synced from Gmail or Drive *** #### Each Seed Contains * **Original Content:** Text, media, or data you added * **Metadata:** Title, source, date captured, type, and tags * **AI Embeddings:** Semantic representation for deep search and recall * **Context Links:** Relationships between similar or related Seeds Your Seeds form a living, connected memory graph.\ myNeutron and your connected AIs can query, learn from, and summarize this graph. *** #### Why Seeds Matter Traditional notes and files stay static.\ Seeds are portable, searchable, and ready for AI use.\ They can be accessed by any AI tool through myNeutron’s **Model Context Protocol (MCP).** | Without myNeutron | With myNeutron | | ----------------------------- | -------------------------------------- | | Notes stay trapped in one app | Knowledge is portable across tools | | Search is keyword-based | Search understands meaning and context | | Files and emails are separate | All unified as Seeds in one workspace | --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://neutron-4.gitbook.io/neutron-docs/getting-started/seeds-the-foundation-of-myneutron.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.