API Reference

Memory Layers

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Entries

MemoryService manages memory layers and their entries at the WORKSPACE level. Layers are named containers that can be composed into an objective's memory stack; entries are the keyed values within a layer.

All operations are implicitly scoped to the workspace determined by the JWT token. System-managed layers (e.g., episodic layers created by the runtime) cannot be mutated through this API.

Authentication: Bearer token (JWT) Scope: Workspace-level operations

List memory entries

GET/v1/memory_layers/{memoryLayerId}/entries

Create a new memory entry

POST/v1/memory_layers/{memoryLayerId}/entries

Get a memory entry by ID

GET/v1/memory_layers/{memoryLayerId}/entries/{id}

Update a memory entry

PATCH/v1/memory_layers/{memoryLayerId}/entries/{id}

Delete a memory entry

DELETE/v1/memory_layers/{memoryLayerId}/entries/{id}

ModelsExpand Collapse

MemoryEntry = object { metadata, spec, info }

MemoryEntry is a single keyed value within a MemoryLayer. Entries are addressed by their key, which follows the S3 object key safe-character convention (see MemoryEntrySpec.key for the full rule). Keys are unique within a single layer; the same key may appear in multiple layers, in which case the LIFO stack-walk determines which one wins for a given objective.

MemoryEntry is the summary shape, returned by ListMemoryEntries. It does not carry the entry body — callers that need the body must fetch the entry individually via GetMemoryEntry, which returns a MemoryEntryDetail.

metadata: ResourceMetadata { id, accountId, createdAt, 5 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

spec: MemoryEntrySpec { key, description, title }

MemoryEntrySpec is the metadata portion of an entry — the fields that identify and describe it, without the body. It appears on both the summary (MemoryEntry) and detail (MemoryEntryDetail) views.

key: string

The lookup key for this entry within its layer. Must conform to the S3 object key safe-characters spec: ASCII alphanumerics and the special characters !, -, _, ., *, ', (, ), and /. Forward slashes may be used to suggest hierarchy (e.g., "skills/postmortem/write"), but lookups are flat — the key is a single opaque string, not a path.

Additional rules enforced by the service:

• May not begin or end with /
• May not contain consecutive slashes (//)
• May not begin with reserved prefixes (cadenya/, system/)
• Case-sensitive
• Unique within the parent layer

For skills entries, this key is also the id the model passes to memory_load_skill when it decides to load the entry's content.

description: optional string

One-line "when to use this" hint shown in the frontmatter manifest for skills entries. The model uses this to decide whether to load the body, so it should be written for the model as the audience. Ignored for layer types that do not advertise frontmatter.

title: optional string

Short human/LLM-readable title shown in the frontmatter manifest for skills entries. Ignored for layer types that do not advertise frontmatter.

info: optional MemoryEntryInfo { createdBy, memoryLayer }

createdBy: optional Profile { metadata, spec }

Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

spec: ProfileSpec { type, email, name }

ProfileSpec contains the profile-specific fields

type: "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"

Type is the type of profile. User's are humans, API keys are computers. You know the deal.

formatenum

One of the following:

"PROFILE_TYPE_USER"

"PROFILE_TYPE_API_KEY"

"PROFILE_TYPE_SYSTEM"

email: optional string

Email address of the user (required, unique per account)

name: optional string

Display name for the user (e.g., "Bobby Tables")

memoryLayer: optional ResourceMetadata { id, accountId, createdAt, 5 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

MemoryEntryCreateSpec = object { key, content, description, 2 more }

MemoryEntryCreateSpec is the input shape for CreateMemoryEntry. It accepts either inline content or a reference to a completed Upload; exactly one of the two must be set.

key: string

See MemoryEntrySpec.key for the full rule set. Same constraints apply here.

content: optional string

Inline content, written directly into the entry.

description: optional string

title: optional string

uploadId: optional string

ID of a COMPLETE Upload. The server reads the object from storage, copies its bytes into the entry, and marks the upload consumed.

MemoryEntryDetail = object { content, metadata, spec, info }

MemoryEntryDetail is the full representation of an entry, including the resolved content body. Returned by GetMemoryEntry, CreateMemoryEntry, and UpdateMemoryEntry.

content: string

The resolved body of the entry. For entries created or updated via an upload_id, this is the ingested content, not the original upload handle. May be empty; an entry with only a key, title, and description is valid (e.g., a stub skill being drafted, or an entry where the frontmatter alone is the payload).

metadata: ResourceMetadata { id, accountId, createdAt, 5 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

spec: MemoryEntrySpec { key, description, title }

MemoryEntrySpec is the metadata portion of an entry — the fields that identify and describe it, without the body. It appears on both the summary (MemoryEntry) and detail (MemoryEntryDetail) views.

key: string

The lookup key for this entry within its layer. Must conform to the S3 object key safe-characters spec: ASCII alphanumerics and the special characters !, -, _, ., *, ', (, ), and /. Forward slashes may be used to suggest hierarchy (e.g., "skills/postmortem/write"), but lookups are flat — the key is a single opaque string, not a path.

Additional rules enforced by the service:

• May not begin or end with /
• May not contain consecutive slashes (//)
• May not begin with reserved prefixes (cadenya/, system/)
• Case-sensitive
• Unique within the parent layer

For skills entries, this key is also the id the model passes to memory_load_skill when it decides to load the entry's content.

description: optional string

One-line "when to use this" hint shown in the frontmatter manifest for skills entries. The model uses this to decide whether to load the body, so it should be written for the model as the audience. Ignored for layer types that do not advertise frontmatter.

title: optional string

Short human/LLM-readable title shown in the frontmatter manifest for skills entries. Ignored for layer types that do not advertise frontmatter.

info: optional MemoryEntryInfo { createdBy, memoryLayer }

createdBy: optional Profile { metadata, spec }

Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

spec: ProfileSpec { type, email, name }

ProfileSpec contains the profile-specific fields

type: "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"

Type is the type of profile. User's are humans, API keys are computers. You know the deal.

formatenum

One of the following:

"PROFILE_TYPE_USER"

"PROFILE_TYPE_API_KEY"

"PROFILE_TYPE_SYSTEM"

email: optional string

Email address of the user (required, unique per account)

name: optional string

Display name for the user (e.g., "Bobby Tables")

memoryLayer: optional ResourceMetadata { id, accountId, createdAt, 5 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

MemoryEntryInfo = object { createdBy, memoryLayer }

createdBy: optional Profile { metadata, spec }

Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

spec: ProfileSpec { type, email, name }

ProfileSpec contains the profile-specific fields

type: "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"

Type is the type of profile. User's are humans, API keys are computers. You know the deal.

formatenum

One of the following:

"PROFILE_TYPE_USER"

"PROFILE_TYPE_API_KEY"

"PROFILE_TYPE_SYSTEM"

email: optional string

Email address of the user (required, unique per account)

name: optional string

Display name for the user (e.g., "Bobby Tables")

memoryLayer: optional ResourceMetadata { id, accountId, createdAt, 5 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

externalId: optional string

External ID for the resource (e.g., a workflow ID from an external system)

labels: optional map[string]

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

MemoryEntrySpec = object { key, description, title }

MemoryEntrySpec is the metadata portion of an entry — the fields that identify and describe it, without the body. It appears on both the summary (MemoryEntry) and detail (MemoryEntryDetail) views.

key: string

The lookup key for this entry within its layer. Must conform to the S3 object key safe-characters spec: ASCII alphanumerics and the special characters !, -, _, ., *, ', (, ), and /. Forward slashes may be used to suggest hierarchy (e.g., "skills/postmortem/write"), but lookups are flat — the key is a single opaque string, not a path.

Additional rules enforced by the service:

• May not begin or end with /
• May not contain consecutive slashes (//)
• May not begin with reserved prefixes (cadenya/, system/)
• Case-sensitive
• Unique within the parent layer

For skills entries, this key is also the id the model passes to memory_load_skill when it decides to load the entry's content.

description: optional string

One-line "when to use this" hint shown in the frontmatter manifest for skills entries. The model uses this to decide whether to load the body, so it should be written for the model as the audience. Ignored for layer types that do not advertise frontmatter.

title: optional string

Short human/LLM-readable title shown in the frontmatter manifest for skills entries. Ignored for layer types that do not advertise frontmatter.

MemoryEntryUpdateSpec = object { content, description, key, 2 more }

MemoryEntryUpdateSpec is the input shape for UpdateMemoryEntry. Fields present in the request's update_mask are applied; unset fields are left alone. The source oneof is optional for updates — omit it to leave the body untouched, or set exactly one branch to replace it.

content: optional string

description: optional string

key: optional string

title: optional string

uploadId: optional string