> ## Documentation Index
> Fetch the complete documentation index at: https://docs.replicas.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Long-term memory

> Carry personal preferences, team decisions, and lessons from past work into future workspaces.

Replicas learns from completed work so you spend less time repeating preferences, explaining past decisions, and correcting the same mistakes. Long-term memory is available to every organization and carries context across workspaces and coding agents.

## What gets remembered

Memory keeps information that can help with future tasks: your preferred way of working, repository conventions, technical decisions, procedures that worked, and fixes for recurring failures. It is selective, rather than a copy of every conversation.

| Scope        | What it contains                                                     | Where it is used                              |
| ------------ | -------------------------------------------------------------------- | --------------------------------------------- |
| Personal     | Your preferences, project context, and lessons from your work        | Workspaces you create within the organization |
| Organization | Team conventions, shared decisions, and reusable technical knowledge | Workspaces across your organization           |

Personal memory is associated with your seat in the organization. Chats involving multiple people contribute organization memory without being assigned to one person's memory. Organization summaries are filtered to exclude personal context and sensitive information; credentials and secrets are excluded from both scopes.

## How memory builds

<Steps>
  <Step title="Work with your agent">
    Give feedback and explain decisions as you work. For example: “Use the existing pagination component, and verify this flow in the browser before opening a PR.”
  </Step>

  <Step title="Let the workspace sleep">
    When a workspace with memory retention enabled [sleeps](/features/workspaces/overview#sleep-and-wake), Replicas captures eligible chats and extracts useful lessons. Background processing combines these summaries into personal and organization memory.
  </Step>

  <Step title="Start the next task">
    Replicas loads the latest published memory when a workspace starts or wakes. Agents search for relevant context before substantive work and can consult the supporting summaries for detail.
  </Step>
</Steps>

<Note>
  New memories currently come from **Claude Code and Codex chats**. Forked chats do not contribute new memories. Other coding agents can recall existing memory. Processing runs in the background, so a workspace that wakes immediately may receive the previous version.
</Note>

Memory processing uses your connected [Claude Code](/features/coding-agents/claude-code) or [Codex](/features/coding-agents/codex) credentials. Keep the relevant subscription or API key connected so new memories can be processed.

## Control what contributes

Recalling existing memory and retaining new work are separate controls.

| Workspace source                                  | Retain new work by default |
| ------------------------------------------------- | -------------------------- |
| Dashboard, desktop, mobile, and integration tasks | On                         |
| Automations and API-created workspaces            | Off                        |

For an [automation](/features/automations), open **Advanced settings → Memory** and enable **Retain workspace memory** to include its runs in future memory. Through the [API](/features/api), set `config.memoryRetentionEnabled` when creating a workspace.

Turning retention off prevents that workspace's work from contributing new memories. It can still recall existing organization and personal memory.

The organization-wide **Save chat and Canvas history** setting also applies: when history saving is disabled, Replicas does not persist new chats for memory or load saved memory into workspaces. See [Data retention](/admin/data-retention).

## Inspect and use memory

Ask your agent to explain the context it found:

```text theme={null}
Check memory for our release process. Summarize the relevant decisions and cite the supporting past work before making changes.
```

You can also read the files in the workspace terminal:

```bash theme={null}
cat ~/.replicas/memories/seat/MEMORY.md
cat ~/.replicas/memories/organization/MEMORY.md
```

Each scope includes a `rollout_summaries/` directory with supporting summaries. These files are generated and installed as read-only context. Give corrections in chat so future memory can reflect them; editing a local copy does not update shared memory.

<Tip>
  Memory is historical context and can be incomplete or outdated. Current instructions take priority. Keep requirements that must always apply in your repository's [agent instructions](/features/workspaces/repository-configuration).
</Tip>