> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/technical-reference/models-agents-and-skills/memory-reset-and-persistence.md).

# Memory Reset and Persistence

A memory reset removes stored conversation entries for a selected scope. It does not remove knowledge sources or necessarily delete the visible conversation.

{% embed url="<https://1957915746-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FY3c8DbKYMLxA5OltcreC%2Fmemory-reset-and-persistence.mp4?alt=media&token=4238f51e-75ec-4d73-9e17-3969c38e6bbe>" %}
A short walkthrough of memory reset and persistence.
{% endembed %}

## Before you begin

Permission to clear the relevant memory and the project, node, and conversation scope to clear.

## Key concepts

| Term                | Definition                                                                                                                                                                 |
| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Memory reset        | Removal of stored memory for the selected scope. It does not remove the current prompt, knowledge sources, or unrelated conversations.                                     |
| Memory scope        | The project, node, and conversation context in which earlier exchanges can be reused. Keep unrelated users and conversations separate using the supported identity fields. |
| Conversation memory | Earlier exchanges made available for later requests in the configured scope. Saved messages and the context used for an individual response are not identical.             |
| Instructions        | Directions that define the task, constraints, and expected response. Keep them distinct from source text or tool results used as evidence.                                 |

## Clear conversation memory

1. Identify the node and conversation whose memory should be reset.
2. Use the supported clear-memory control for that scope.
3. Send the next request and inspect whether any repeated information comes from the prompt, a source, or another node.

The selected stored history no longer supplies those earlier messages.

## Behavior and limitations

Clearing memory for one node or conversation does not clear every project or user. Instructions, current inputs, retrieved files, and tool results can still contain the same information after a reset. Deleting a visible conversation and resetting a workflow node’s memory are separate operations.

## Related resources

[Model Settings and Supported Capabilities](https://docs.stackai.com/technical-reference/models-agents-and-skills/model-settings-and-supported-capabilities.md)


---

# 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.stackai.com/technical-reference/models-agents-and-skills/memory-reset-and-persistence.md?ask=<question>&goal=<user_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.
