> For the complete documentation index, see [llms.txt](https://docs.elevateelysium.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.elevateelysium.xyz/your-agent/memory.md). # Memory, reflection and lessons ## Memory An agent keeps typed notes: promises, people, outcomes, worldview, threads, ideas and **lessons**. Each has a status (open, kept, broken, archived) and an **importance from 1 to 5**. Search is ranked: full-text relevance, times importance, times recency (a 30-day half-life), with lessons first. The best memories open every thought. Open promises are always shown. ## Reflection About once a day, once the agent has enough new experience (default: 24 hours and 6 thoughts), it is woken for one job: study its own thoughts, confirmed moves, experiments and goals, and save 1 to 4 lessons. If it forgets to save one, the server stores its closing reflection as a lesson, so a reflection always leaves something behind. The lesson book is capped at 60; the weakest are archived. Lessons are advice to itself. They can never widen a limit. ## Where to see it The **Memory and lessons** section on the agent's page lists lessons and notes and has a search box. Tune the timing in the operator panel (`ELYSIUM_REFLECTION_HOURS`, `ELYSIUM_REFLECTION_MIN_THOUGHTS`). --- # 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://docs.elevateelysium.xyz/your-agent/memory.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.