> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/build-and-improve/intelligence/memory.md).

# Memory

Memory is persistent Project context that can help the Agent across sessions. Use it for context that is useful beyond one conversation, without treating it as the authoritative store for exact operational records, governed policy or maintained mappings.

Memory is a builder surface: Project Builders and Owners can open and edit it. Operators cannot open the Memory page.

## What the Memory surface shows

The current Memory view is a visual canvas with three layers, drawn from top to bottom as **Knowledge**, **Memories** and **Observations**.

The product describes the layers this way:

* **Knowledge** is settled reference: curated articles, skills and rules.
* **Memories** are distilled, reusable facts, preferences and rules of thumb.
* **Observations** are raw, recent material from past sessions, reflections and ingested files.

The panel beside the canvas lets you search persistent context and filter by layer. Projects can also show additional category filters derived from their own data; those categories are not a fixed product taxonomy.

The three layers represent different kinds of persistent context, not a universal source-of-truth hierarchy. A live system record can still be more authoritative than something stored in Memory.

## Inspect and correct persistent context

Select a memory document to inspect it. Builders can edit an existing document from its detail view when persistent context has become stale, misleading or too broad.

There is currently no general **New memory** or **Delete** control on this page. New persistent context is created through Agent work, onboarding and supported ingestion paths rather than by manually adding arbitrary Memory entries here.

## Starting an empty Project

When a Project has no persistent context yet, Memory becomes an onboarding surface rather than an empty list. It can prompt a builder to add organisation background, connect tools and upload useful files.

These steps give the Project material to work with. They do not mean every ingested item becomes trusted Knowledge or that Lleverage automatically discovers the correct operating model. Builders still decide what is authoritative, what belongs in a maintained source, and what the Agent should verify before acting.

## What belongs here

A useful rule:

* exact business record → source system;
* maintained reference document → Knowledge Base;
* maintained structured mapping → Table;
* reusable operating method → Skill;
* useful persistent Project or session context → Memory.

Memory can influence future Agent work, so keep durable facts and preferences here only when they are genuinely reusable. For what operators see during a live Agent session, use the Agent session workspace rather than this builder surface.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.lleverage.ai/build-and-improve/intelligence/memory.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.