ByteChef LogoByteChef
SettingsAI

Memories

View, edit, and delete the durable facts your AI agents remember across conversations - the management surface for Auto Memory.

The Memories page manages Auto Memory: the long-term facts an AI agent decides to keep and reuses in later conversations. The Auto Memory tool lets an agent write memories at runtime. This page lets you read, correct, and delete them.

Agents create memory entries. This page has no button to create one. Use it to review what an agent has stored, correct an outdated fact, change an entry's type, or delete an entry the agent should no longer use.


Auto Memory vs. this page

Where it happensWho acts
Writing a memoryAn agent calls the Auto Memory tool mid-runThe agent, automatically
Managing memoriesThe Memories page (Settings → Current Workspace → Memories, /automation/settings/ai/memories)You

Auto Memory complements chat memory: chat memory replays the current conversation, while Auto Memory persists facts across all future conversations of the same scope. See Chat memory vs Auto Memory for the distinction.

The agent sets each entry's name when it first stores the memory, and the name cannot be changed on this page. The title, description, type, and content are editable. To rename an entry, ask an agent that uses the Auto Memory tool to rename it (its MemoryRename tool).


Accessing Memories

Memories live in the Automation settings under Settings → Current Workspace → Memories, because they belong to the current workspace rather than to the whole organization. The page opens at /automation/settings/ai/memories; the older /automation/ai/memories and /embedded/settings/ai/memories addresses redirect there.

The page has no left sidebar of its own. Its header shows the title AI Memories with the description "Facts the agent has stored while working in this workspace.", and on the right:

  • A Search by title or description... box (see Searching).
  • A Filter Memories button that opens a dropdown with two filter groups, Owner and Type (see Filtering).

When a filter other than All is active, its selection is shown as a badge above the table.

Selecting an environment

Memories are environment-scoped: facts stored in one environment (for example DEVELOPMENT) are not used in another (for example PRODUCTION). The page has no environment control of its own: it follows the environment chosen in the environment selector at the top of the main navigation sidebar, next to the ByteChef logo (shown in the Enterprise Edition). Switching environments there reloads the table and the Owner filter with the memories stored for that environment.


Memory types

Every memory carries a type that classifies the kind of fact it holds. The type is shown next to each entry in the agent's memory index and lets you filter this page. It does not limit which memories the agent sees: the agent's index lists entries of every type.

TypeWhat it holds
UserUser profile and preferences, such as role, tone, and default choices.
FeedbackCorrections or confirmed approaches the user asked the agent to apply in future turns.
ProjectDecisions, deadlines, or domain constraints of the ongoing work.
ReferencePointers to external systems, such as dashboards, boards, and external documents.

Viewing the memories table

With the Owner filter on All, the table lists the memories you can address in the current workspace and environment: your own memories plus the memories of the workspace's project deployments (deployments of embedded connected-user projects are excluded). Memories are ordered by most recently updated, and the list can be narrowed with the filters and search. Each row shows:

ColumnDescription
TitleThe memory's human-readable title, with the immutable name shown beneath it in smaller text.
TypeA badge showing the memory type (User, Feedback, Project, or Reference).
DescriptionThe short one-line summary, truncated to two lines.
UpdatedWhen the memory was last changed, shown as a relative time (for example, "3 days ago").
ActionsA ⋮ menu with Edit and Delete, shown only on rows you can change.

Who can edit and delete

Your own memories can always be edited and deleted. Memories owned by a project deployment change how a live agent behaves on its next run, so only administrators (ROLE_ADMIN) see the ⋮ menu on those rows. Other users can open the row to view the memory.

Empty states

  • When no memories exist for the current workspace and environment and no filter is active, the page shows No memories yet: "AI agents that use the Auto Memory tool store what is worth keeping here, such as user preferences and project decisions. You can inspect, edit or delete each memory."
  • When a filter is active and nothing matches, the page shows "No memories match the selected filters."
  • If the memories cannot be loaded, the page shows Could not load memories with a Retry button. If only the owner list fails to load, a notice reads "Could not load memory owners, so the Owner filter is unavailable." with its own Retry button.

Filtering

Open the Filter Memories dropdown in the header. Owner and Type are independent, so you can pick one value in each group at the same time. Both filters are applied on the server, so changing either one reloads the table.

Owner

  1. All (default) - your own memories plus the memories of the workspace's project deployments.
  2. My memories - only your own memories.
  3. One entry per project deployment that holds memories in this environment, labelled with the deployment's name (or Deployment <id> if the deployment was deleted while its memories remain).

Only owners that actually hold memories in the current environment are listed. The Owner group is not shown at all when no owner holds any memories.

Type

  1. All (default) - show every memory type.
  2. User
  3. Feedback
  4. Project
  5. Reference

Searching

Type into the Search by title or description... box in the header to filter the visible rows. Search matches against both the title and the description of each memory and runs on top of the active filters. Clearing the box restores the full (filtered) list. If the search matches nothing, the table shows "No memories match your search."


Viewing a memory

  1. Click the memory's row (or focus it and press Enter).
  2. The detail dialog opens, showing:
    • The memory title and its type badge in the header.
    • The line Name: ... - Updated ... beneath the title.
    • The description (if set).
    • The full content, rendered from Markdown.
  3. Close the dialog with the close button or Esc.

Editing a memory

  1. Click the ⋮ button on a memory's row and choose Edit. (On deployment-owned memories, the menu is shown only to administrators. See Who can edit and delete.)

  2. The Edit memory dialog opens, pre-filled with the memory's current values.

  3. Change any of the editable fields:

    FieldEditableNotes
    NameNoImmutable here. To rename a memory, ask an agent that uses the Auto Memory tool to rename it (MemoryRename). Shown disabled for reference.
    TitleYesRequired. Save stays disabled while the title is empty. Single line, up to 255 characters.
    DescriptionYesOptional one-line summary. Up to 1024 characters.
    TypeYesChoose User, Feedback, Project, or Reference.
    Content (Markdown)YesThe full memory body, edited as Markdown in a monospace text area. Up to 65,536 characters.
  4. Click Save to persist your changes, or Cancel to discard them. If you made no changes, the dialog closes without saving.

On success a "Memory updated" confirmation appears and the table refreshes.

If an agent changes the memory while the dialog is open, the dialog shows "This memory was changed since you opened it", disables Save, and offers a Reload button that loads the newer version and discards your unsaved changes. If the memory is deleted while the dialog is open, the dialog stays open and says your changes cannot be saved.


Deleting a memory

  1. Click the ⋮ button on a memory's row and choose Delete. (On deployment-owned memories, the menu is shown only to administrators. See Who can edit and delete.)
  2. The Delete this memory permanently? dialog opens and warns that the entry will be removed from the agent's long-term memory.
  3. Click Delete permanently to remove the memory, or Cancel to keep it.

On success, a Memory "<title>" deleted confirmation appears and the row disappears from the table.

Deletions here are permanent and cannot be reversed. If you only want to correct a fact, edit it instead of deleting it.


Storage providers

By default, memories are stored in ByteChef's relational database. Self-hosted operators can select where they live with the BYTECHEF_AI_AUTO_MEMORY_PROVIDER environment variable (bytechef.ai.auto-memory.provider):

ProviderWhere memories live
JDBC (default)The ByteChef database. Existing deployments are unaffected.
FILESYSTEMOne JSON file per memory on the server's file system, via the configured file storage.
AWSThe same file-based layout on S3. Requires the Enterprise Edition AWS file-storage module.

Selecting a provider whose file-storage backend is not configured fails at startup instead of falling back to another provider. On every provider, an edit based on an outdated copy of a memory is rejected instead of overwriting the newer one. File backends check this before writing rather than atomically, so two writes racing at the same moment can both land, and two agents creating a memory with the same name at the same moment can both succeed. There is no migration path between providers - switching does not move existing memories.

Memory is stored only by the ByteChef server application. In a microservices (Enterprise Edition) deployment the Auto Memory tool is still offered to agents, but every call returns an error explaining that the installation runs as microservices, which do not store memory, and that memory requires the ByteChef server application.


Frequently Asked Questions (FAQs)

How is this guide?

Last updated on

On this page