Documentation

API reference, MCP tools, and integration guides.

Every snippet below expects a nams_... key. Replace the placeholder with your own.

Sign in to open your workspace - a default key is created for you, and the in-console Quick Start fills it into every snippet automatically. Or generate one on the API Keys page. Keys expire after 90 days.

API keys work as Bearer tokens directly - no exchange step needed.

List entities

curl https://memory.neo4jlabs.com/v1/entities \
  -H "Authorization: Bearer nams_YOUR_API_KEY"

1. Create a conversation

curl -X POST https://memory.neo4jlabs.com/v1/conversations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer nams_YOUR_API_KEY" \
  -d '{"userId": "user-1"}'

# Response: {"id": "conv-abc-123", ...}

2. Add a message

curl -X POST https://memory.neo4jlabs.com/v1/conversations/CONV_ID/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer nams_YOUR_API_KEY" \
  -d '{"role": "user", "content": "John works at Acme Corp in Denver"}'

3. Check extracted entities

curl https://memory.neo4jlabs.com/v1/entities \
  -H "Authorization: Bearer nams_YOUR_API_KEY"

# Returns entities extracted from your messages:
# John (person), Acme Corp (organization), Denver (location)

Install the nams-hooks plugin for your agent CLI - memory turns on automatically, with no manual MCP config. The agent gets all the NAMS memory, ontology, and workspace tools.

Installs nams-hooks as a Claude Code plugin. The plugin bundles the runtime, hook config, and a credential prompt for your API key.

claude plugin marketplace add neo4j-labs/nams-plugins@latest
claude plugin install nams-hooks@nams-plugins

Then configure and reload it inside Claude Code:

/plugin configure nams-hooks@nams-plugins
/reload-plugins

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

/nams-hooks:nams:workspace use <workspace-id-or-name>

Installs nams-hooks as a Gemini extension from the latest release.

gemini extensions install https://github.com/neo4j-labs/nams-plugins --ref latest

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

/nams:workspace use <workspace-id-or-name>

Adds the nams-plugins marketplace. Restart Codex, open /plugins, install “NAMS Hooks”, then /hooks to trust the bundled hooks.

codex plugin marketplace add neo4j-labs/nams-plugins@latest
codex plugin marketplace list

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

$nams:workspace use <workspace-id-or-name>

Installs the npm package and drops the hook shim into your project's .opencode/plugins.

npm install -g @neo4j-labs/nams-plugins
cp "$(npm root -g)/@neo4j-labs/nams-plugins/templates/opencode/.opencode/plugins/nams-hooks.js" \
  .opencode/plugins/nams-hooks.js

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

nams-hooks workspaces configure opencode --scope session --session-id <id> --workspace <name>

Prefer a raw MCP client config (Claude Desktop, Cursor, Windsurf…)? See the Plugins or MCP Tools tab.

Prefer OAuth 2.0?

MCP clients that support OAuth can authenticate interactively with PKCE - no static key to manage. Discovery endpoints:

# Protected Resource Metadata (RFC 9728)
https://memory.neo4jlabs.com/mcp/.well-known/oauth-protected-resource

# Authorization Server Metadata (RFC 8414)
https://memory.neo4jlabs.com/mcp/.well-known/oauth-authorization-server

# Dynamic Client Registration (RFC 7591)
POST https://memory.neo4jlabs.com/mcp/oauth/register

Access tokens are short-lived (1 hour); clients refresh automatically.

API	`https://memory.neo4jlabs.com/v1`
Auth	`https://memory.neo4jlabs.com/v1/auth`
MCP	`https://memory.neo4jlabs.com/mcp`

The nams-hooks plugin wires NAMS memory straight into your agent CLI - every turn is captured and recalled automatically, no manual MCP config. One package supports Claude Code, Gemini CLI, Codex, and OpenCode.

Prerequisites: Node.js 20+, a NAMS API key, and a base URL (https://memory.neo4jlabs.com). A workspace ID is optional - with a single workspace the plugin auto-selects it.

View nams-plugins on GitHub →

Pick your agent below. Each tab has the install command plus how to select a workspace.

Installs nams-hooks as a Claude Code plugin. The plugin bundles the runtime, hook config, and a credential prompt for your API key.

claude plugin marketplace add neo4j-labs/nams-plugins@latest
claude plugin install nams-hooks@nams-plugins

Then configure and reload it inside Claude Code:

/plugin configure nams-hooks@nams-plugins
/reload-plugins

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

/nams-hooks:nams:workspace use <workspace-id-or-name>

Installs nams-hooks as a Gemini extension from the latest release.

gemini extensions install https://github.com/neo4j-labs/nams-plugins --ref latest

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

/nams:workspace use <workspace-id-or-name>

Adds the nams-plugins marketplace. Restart Codex, open /plugins, install “NAMS Hooks”, then /hooks to trust the bundled hooks.

codex plugin marketplace add neo4j-labs/nams-plugins@latest
codex plugin marketplace list

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

$nams:workspace use <workspace-id-or-name>

Installs the npm package and drops the hook shim into your project's .opencode/plugins.

npm install -g @neo4j-labs/nams-plugins
cp "$(npm root -g)/@neo4j-labs/nams-plugins/templates/opencode/.opencode/plugins/nams-hooks.js" \
  .opencode/plugins/nams-hooks.js

Set NAMS_API_KEY (and NAMS_BASE_URL=https://memory.neo4jlabs.com) via the plugin's credential prompt, ~/.nams/config.json, or environment variables. Then pick a workspace:

nams-hooks workspaces configure opencode --scope session --session-id <id> --workspace <name>

Runtime config is JSON-first. Drop a user-local ~/.nams/config.json (or a project-local .nams/config.json):

{
  "apiKey": "nams_...",
  "workspaceId": "<workspace-id>",
  "baseUrl": "https://memory.neo4jlabs.com"
}

Environment variables (final overrides)

NAMS_API_KEY · NAMS_WORKSPACE_ID · NAMS_BASE_URL

Keep any file containing an API key gitignored. Prefer a manual MCP client config instead? See the MCP Tools tab. Full docs live in the nams-plugins repo.

Paste your API key in any endpoint's "Try it" panel to run requests against your workspace.

GET/.well-known/jwks.json

Get public keys (JWKS)

GET/v1/auth/api-keys

List API keys

POST/v1/auth/api-keys

Create an API key

DELETE/v1/auth/api-keys/{id}

Revoke an API key

Auth service base URL: https://memory.neo4jlabs.com Revoke an API key by ID. The key is immediately invalidated - any active JWTs issued from it are blocklisted. This action is irreversible. Owner-only: only the user who owns the key can revoke it. Non-owners receive 404 (indistinguishable from a missing key) to prevent key-id enumeration. Auth: requires a user token or an Admin API key (workspace:admin); workspace-bound data keys are rejected with 403.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	API key ID

curl

curl -X DELETE 'https://memory.neo4jlabs.com/v1/auth/api-keys/{id}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns status: revoked

{
  "status": "success"
}

401

No user in token

{
  "error": "No user in token"
}

403

Requires a user token or an Admin API key

{
  "error": "Requires a user token or an Admin API key"
}

404

Key not found or not owned by caller

{
  "error": "Key not found or not owned by caller"
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/auth/api-keys/{id}/reveal

Reveal a stored API key

Auth service base URL: https://memory.neo4jlabs.com Returns the decrypted raw API key value for keys created with encrypted storage. Owner-only: only the user who owns the key can reveal it. Non-owners receive 404 (indistinguishable from a missing key) to prevent credential disclosure and key-id enumeration. Returns 410 if the key was revoked or predates encrypted storage. Auth: requires a user token or an Admin API key (workspace:admin); workspace-bound data keys are rejected with 403.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	API key ID

curl

curl 'https://memory.neo4jlabs.com/v1/auth/api-keys/{id}/reveal' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Key ID and decrypted raw key

{
  "id": "string",
  "key": "string"
}

401

No user in token

{
  "error": "No user in token"
}

403

Requires a user token or an Admin API key

{
  "error": "Requires a user token or an Admin API key"
}

404

Key not found or not owned by caller

{
  "error": "Key not found or not owned by caller"
}

410

Key revoked or not revealable

{
  "error": "Key revoked or not revealable"
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/auth/api-keys/{id}/rotate

Rotate an API key

Auth service base URL: https://memory.neo4jlabs.com Mint a new API key inheriting the old key's label and scopes, and atomically revoke the old one. The new raw key is returned exactly once in the response (and is also persisted encrypted-at-rest so it can be revealed again later). Owner-only: only the user who owns the key can rotate it. Non-owners receive 404 (indistinguishable from a missing key) to prevent key-id enumeration. Auth: requires a user token or an Admin API key (workspace:admin); workspace-bound data keys are rejected with 403.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	API key ID to rotate

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/auth/api-keys/{id}/rotate' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

New key ID, new raw key (save this), and inherited label

{
  "id": "string",
  "key": "string",
  "label": "string"
}

401

No user in token

{
  "error": "No user in token"
}

403

Requires a user token or an Admin API key

{
  "error": "Requires a user token or an Admin API key"
}

404

Key not found or not owned by caller

{
  "error": "Key not found or not owned by caller"
}

410

Key is already revoked

{
  "error": "Key is already revoked"
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/auth/exchange

Exchange Auth0 token for NAMS JWTs

Auth service base URL: https://memory.neo4jlabs.com Validate an Auth0 Bearer token via JWKS and return per-workspace NAMS JWTs. Automatically provisions a default workspace for first-time users. Returns an array of {workspace_id, token} pairs - one per workspace the user belongs to.

Parameters

Name	In	Type	Required	Description
`Authorization`	header	string	required	Auth0 Bearer token

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/auth/exchange' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns workspaces array with workspace_id and token

{
  "workspaces": [
    "..."
  ]
}

401

Invalid or missing token

{
  "error": "Invalid or missing token"
}

500

Internal error

{
  "error": "Internal error"
}

501

Auth0 exchange not configured

{
  "error": "Auth0 exchange not configured"
}

POST/v1/auth/oauth/callback

OAuth2 callback (not yet implemented)

POST/v1/auth/refresh

Refresh an access token

GET/v1/conversations

List conversations

List conversations for the workspace, newest first. Returns metadata only (no message bodies), plus a display title and firstMessageSnippet per conversation. The title is read from the conversation's metadata "title" key (set metadata.title at creation to give a conversation a display name); firstMessageSnippet is the first message's content truncated to 120 characters. Both are empty strings when unset.

Parameters

Name	In	Type	Required	Description
`limit`	query	integer	optional	Max conversations to return (1-200, default 50)

curl

curl 'https://memory.neo4jlabs.com/v1/conversations' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns conversations array

{
  "conversations": [
    "..."
  ]
}

404

Workspace not found

{
  "error": "Workspace not found"
}

409

Workspace database removed (database_unavailable) - reprovision or update the external connection

{
  "error": "Workspace database removed (database_unavailable) - reprovision or update the external connection",
  "message": "the workspace database is unreachable or has been removed; reprovision it or update the external connection",
  "workspaceId": "b3f1c2d4-5e6f-7a8b-9c0d-1e2f3a4b5c6d"
}

500

Internal error (cypher_error or internal)

{
  "error": "Internal error (cypher_error or internal)",
  "message": "the workspace database is unreachable or has been removed; reprovision it or update the external connection",
  "workspaceId": "b3f1c2d4-5e6f-7a8b-9c0d-1e2f3a4b5c6d"
}

503

Workspace database unreachable (db_unreachable); also returned as {error: workspace_not_provisioned, status, statusMessage} while the workspace is provisioning

{
  "error": "Workspace database unreachable (db_unreachable); also returned as {error: workspace_not_provisioned, status, statusMessage} while the workspace is provisioning",
  "message": "the workspace database is unreachable or has been removed; reprovision it or update the external connection",
  "workspaceId": "b3f1c2d4-5e6f-7a8b-9c0d-1e2f3a4b5c6d"
}

POST/v1/conversations

Create a conversation

DELETE/v1/conversations/{id}

Delete a conversation

Delete a conversation and all its messages.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID

curl

curl -X DELETE 'https://memory.neo4jlabs.com/v1/conversations/{id}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns status: deleted

{
  "status": "success"
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/conversations/{id}

Get a conversation

Get conversation metadata by ID.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID

curl

curl 'https://memory.neo4jlabs.com/v1/conversations/{id}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns id, workspaceId, userId, metadata, createdAt, updatedAt

{
  "createdAt": "string",
  "id": "string",
  "metadata": {},
  "updatedAt": "string",
  "userId": "string",
  "workspaceId": "string"
}

404

Not found

{
  "error": "Not found"
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/conversations/{id}/context

Get three-tier context

Get the structured context for an agent to build its prompt from. Returns three tiers: (1) reflections - highest-level compressed insights, (2) observations - mid-level summaries, (3) recentMessages - raw recent messages. Call this before constructing an agent's system prompt.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID

curl

curl 'https://memory.neo4jlabs.com/v1/conversations/{id}/context' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns reflections, observations, recentMessages arrays

{
  "observations": [
    "..."
  ],
  "recentMessages": [
    "..."
  ],
  "reflections": [
    "..."
  ]
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/conversations/{id}/messages

List messages

List messages in a conversation, newest first. Use the limit parameter to control page size (default 50, max 200).

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID
`limit`	query	integer	optional	Max messages to return (1-200, default 50)

curl

curl 'https://memory.neo4jlabs.com/v1/conversations/{id}/messages' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns messages array

{
  "messages": [
    "..."
  ]
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/conversations/{id}/messages

Add a message

Add a message to a conversation. Triggers asynchronous entity extraction via the memory worker. Role must be "user", "assistant", or "system".

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID

Request Body

{
  "content": "string",
  "role": "string"
}

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/conversations/{id}/messages' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{
  "content": "",
  "role": ""
}'

Responses

201

Returns id, conversationId, role, content

{
  "content": "string",
  "conversationId": "string",
  "id": "string",
  "role": "string"
}

400

Invalid role or missing fields

{
  "error": "Invalid role or missing fields"
}

404

Conversation not found

{
  "error": "Conversation not found"
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/conversations/{id}/messages/bulk

Add messages in bulk

Add multiple messages to a conversation in a single request. Each message triggers async entity extraction independently. Maximum 100 messages per request.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID

Request Body

{
  "messages": [
    "..."
  ]
}

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/conversations/{id}/messages/bulk' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{
  "messages": [
    {
      "content": "",
      "role": ""
    }
  ]
}'

Responses

201

Returns messages array with IDs

{
  "messages": [
    "..."
  ]
}

400

Validation error

{
  "error": "Validation error"
}

404

Conversation not found

{
  "error": "Conversation not found"
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/conversations/{id}/search

Search messages

Search messages within a conversation by content. Uses vector similarity search when embeddings are available, falling back to text CONTAINS. Returns searchType field indicating which method was used.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID

Request Body

{
  "limit": 0,
  "query": "string"
}

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/conversations/{id}/search' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{
  "query": ""
}'

Responses

200

Returns messages array and searchType

{
  "messages": [
    "..."
  ],
  "searchType": "vector"
}

400

Missing query

{
  "error": "Missing query"
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/entities

List entities

List all entities in the knowledge graph. Filter by type using the optional query parameter.

Parameters

Name	In	Type	Required	Description
`type`	query	string	optional	Filter by type: person, organization, location, concept, tool, custom

curl

curl 'https://memory.neo4jlabs.com/v1/entities' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns entities array

{
  "entities": [
    "..."
  ]
}

404

Workspace not found

{
  "error": "Workspace not found"
}

409

Workspace database removed (database_unavailable) - reprovision or update the external connection

{
  "error": "Workspace database removed (database_unavailable) - reprovision or update the external connection",
  "message": "the workspace database is unreachable or has been removed; reprovision it or update the external connection",
  "workspaceId": "b3f1c2d4-5e6f-7a8b-9c0d-1e2f3a4b5c6d"
}

500

Internal error (cypher_error or internal)

{
  "error": "Internal error (cypher_error or internal)",
  "message": "the workspace database is unreachable or has been removed; reprovision it or update the external connection",
  "workspaceId": "b3f1c2d4-5e6f-7a8b-9c0d-1e2f3a4b5c6d"
}

503

Workspace database unreachable (db_unreachable); also returned as {error: workspace_not_provisioned, status, statusMessage} while the workspace is provisioning

{
  "error": "Workspace database unreachable (db_unreachable); also returned as {error: workspace_not_provisioned, status, statusMessage} while the workspace is provisioning",
  "message": "the workspace database is unreachable or has been removed; reprovision it or update the external connection",
  "workspaceId": "b3f1c2d4-5e6f-7a8b-9c0d-1e2f3a4b5c6d"
}

POST/v1/entities

Create an entity

GET/v1/entities/count

Count entities

GET/v1/entities/graph

Get entity graph

POST/v1/entities/search

Search entities

DELETE/v1/entities/{id}

Delete an entity

Delete an entity and all its relationships from the knowledge graph.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Entity ID

curl

curl -X DELETE 'https://memory.neo4jlabs.com/v1/entities/{id}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns status: deleted

{
  "status": "success"
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/entities/{id}

Get an entity

Get entity details including all relationships (incoming and outgoing edges in the knowledge graph).

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Entity ID

curl

curl 'https://memory.neo4jlabs.com/v1/entities/{id}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns entity fields and relationships array

{
  "confidence": 0,
  "createdAt": "string",
  "description": "string",
  "id": "string",
  "name": "string",
  "relationships": [
    "..."
  ],
  "sourceStage": "string",
  "type": "string",
  "updatedAt": "string"
}

404

Not found

{
  "error": "Not found"
}

500

Internal error

{
  "error": "Internal error"
}

PUT/v1/entities/{id}

Update an entity

Update an entity's name or description.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Entity ID

Request Body

{
  "description": "string",
  "name": "string"
}

curl

curl -X PUT 'https://memory.neo4jlabs.com/v1/entities/{id}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{}'

Responses

200

Returns status: updated

{
  "status": "success"
}

400

Invalid request

{
  "error": "Invalid request"
}

500

Internal error

{
  "error": "Internal error"
}

PUT/v1/entities/{id}/feedback

Score an entity

Provide feedback on entity quality. userScore is a float 0-1 representing confidence. confirmed=true marks the entity as human-verified.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Entity ID

Request Body

{
  "confirmed": false,
  "userScore": 0
}

curl

curl -X PUT 'https://memory.neo4jlabs.com/v1/entities/{id}/feedback' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{}'

Responses

200

Returns id, updated: true

{
  "id": "string",
  "updated": false
}

400

Invalid request

{
  "error": "Invalid request"
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/entities/{id}/history

Get entity history

Get cross-conversation history - all messages that mention this entity, across all conversations in the workspace.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Entity ID

curl

curl 'https://memory.neo4jlabs.com/v1/entities/{id}/history' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns entityId and mentions array

{
  "entityId": "string",
  "mentions": [
    {}
  ]
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/entities/{id}/merge

Merge entities

Merge the source entity into a target entity. All relationships are transferred to the target. A SAME_AS relationship is created for provenance. The source entity is not deleted but becomes inert.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Source entity ID

Request Body

{
  "targetId": "string"
}

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/entities/{id}/merge' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{
  "targetId": ""
}'

Responses

200

Returns status: merged, sourceId, targetId

{
  "sourceId": "string",
  "status": "merged",
  "targetId": "string"
}

400

Missing targetId or attempted self-merge

{
  "error": "Missing targetId or attempted self-merge"
}

404

Target entity not found

{
  "error": "Target entity not found"
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/graph/expand

Expand a graph node

GET/v1/conversations/{id}/observations

List observations

List compressed observations for a conversation. Observations are auto-generated summaries of message windows, created by the memory worker after sufficient messages accumulate.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID
`limit`	query	integer	optional	Max observations to return (1-200, default 50)

curl

curl 'https://memory.neo4jlabs.com/v1/conversations/{id}/observations' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns observations array

{
  "observations": [
    "..."
  ]
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/conversations/{id}/reflections

List reflections

List reflections for a conversation. Reflections are higher-level insights synthesized from multiple observations. Each new reflection supersedes the previous.

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Conversation ID

curl

curl 'https://memory.neo4jlabs.com/v1/conversations/{id}/reflections' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns reflections array

{
  "reflections": [
    "..."
  ]
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/reasoning/explain/{stepId}

Explain a reasoning step

Get a detailed explanation of a reasoning step including its tool calls and the entities it influenced.

Parameters

Name	In	Type	Required	Description
`stepId`	path	string	required	Step ID

curl

curl 'https://memory.neo4jlabs.com/v1/reasoning/explain/{stepId}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns step details, toolCalls, and influencedEntities

{
  "actionTaken": "string",
  "conversationId": "string",
  "createdAt": "string",
  "id": "string",
  "influencedEntities": [
    "..."
  ],
  "reasoning": "string",
  "result": "string",
  "toolCalls": [
    "..."
  ]
}

404

Step not found

{
  "error": "Step not found"
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/reasoning/provenance/{entityId}

Get entity provenance

Get the reasoning chain that influenced the creation of an entity - which steps and tool calls contributed to it.

Parameters

Name	In	Type	Required	Description
`entityId`	path	string	required	Entity ID

curl

curl 'https://memory.neo4jlabs.com/v1/reasoning/provenance/{entityId}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns entityId and provenance chain

{
  "entityId": "string",
  "steps": [
    {}
  ]
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/reasoning/steps

List reasoning steps

List reasoning steps for a conversation. The conversation_id query parameter is required.

Parameters

Name	In	Type	Required	Description
`conversation_id`	query	string	required	Conversation ID

curl

curl 'https://memory.neo4jlabs.com/v1/reasoning/steps' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns steps array

{
  "steps": [
    "..."
  ]
}

400

Missing conversation_id

{
  "error": "Missing conversation_id"
}

500

Internal error

{
  "error": "Internal error"
}

POST/v1/reasoning/steps

Record a reasoning step

POST/v1/reasoning/tool-calls

Record a tool call

GET/v1/reasoning/trace/{conversationId}

Get reasoning trace

Get the full reasoning trace for a conversation - all steps and their tool calls, in order.

Parameters

Name	In	Type	Required	Description
`conversationId`	path	string	required	Conversation ID

curl

curl 'https://memory.neo4jlabs.com/v1/reasoning/trace/{conversationId}' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

Returns conversationId, steps with nested toolCalls

{
  "conversationId": "string",
  "steps": [
    "..."
  ],
  "toolCalls": [
    "..."
  ]
}

500

Internal error

{
  "error": "Internal error"
}

GET/v1/skills

List skills

GET/v1/skills/capabilities

Report enabled skill features and gate thresholds

POST/v1/skills/generate

Generate a skill from workspace memory

GET/v1/skills/governance

Audit the skill corpus (governance)

GET/v1/skills/published

Discover published skills (workspace-scoped)

POST/v1/skills/review/bulk

Bulk-review skills (approve/reject up to 100 in one call)

GET/v1/skills/runs/{id}

Get distillation run status

Name	In	Type	Required	Description
`id`	path	string	required	Run ID

GET/v1/skills/{id}

Get a skill and its versions

GET/v1/skills/{id}/download

Download a skill package (zip)

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl 'https://memory.neo4jlabs.com/v1/skills/{id}/download' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

GET/v1/skills/{id}/drift

Detect skill provenance drift

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl 'https://memory.neo4jlabs.com/v1/skills/{id}/drift' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

POST/v1/skills/{id}/edit

Validate a proposed skill edit (dry run)

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/skills/{id}/edit' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

POST/v1/skills/{id}/edit/commit

Commit a validated skill edit as a new in_review version

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/skills/{id}/edit/commit' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

202

Edit enqueued; returns runId

400

invalid edit

GET/v1/skills/{id}/explain-provenance

Explain a skill's provenance

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl 'https://memory.neo4jlabs.com/v1/skills/{id}/explain-provenance' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

POST/v1/skills/{id}/extract-subprocedure

Extract steps into a reusable sub-procedure skill

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/skills/{id}/extract-subprocedure' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

202

Extraction enqueued; returns runId

POST/v1/skills/{id}/publish

Publish a skill

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/skills/{id}/publish' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

409

not approved

POST/v1/skills/{id}/review

Review a skill (approve/reject)

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

Request Body

{
  "decision": "string",
  "feedback": "string"
}

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/skills/{id}/review' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{}'

Responses

200

POST/v1/skills/{id}/steps/{stepId}/repair

Repair one drifted step of a skill

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID
`stepId`	path	string	required	Step ID

curl

curl -X POST 'https://memory.neo4jlabs.com/v1/skills/{id}/steps/{stepId}/repair' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

202

Repair enqueued; returns runId

GET/v1/skills/{id}/verify

Verify a skill version's attestation

Parameters

Name	In	Type	Required	Description
`id`	path	string	required	Skill ID

curl

curl 'https://memory.neo4jlabs.com/v1/skills/{id}/verify' \
  -H 'Authorization: Bearer nams_YOUR_API_KEY'

Responses

200

POST/v1/query

Execute a read-only Cypher query

GET/v1/users/me/workspaces

List my workspaces

GET/v1/workspace

Get the current workspace

GET/v1/workspace/database

Get database configuration

POST/v1/workspace/database/test

Test an external database connection

GET/v1/workspace/members

List workspace members

GET/v1/workspace/relations

Get typed-relation config

GET/v1/workspace/resolution

Get entity-resolution config

POST/v1/workspaces

Create a workspace

The MCP server uses Streamable HTTP transport and is available at https://memory.neo4jlabs.com/mcp. Pick your client below for a copy-paste config.

Claude Desktop's config does not accept a remote URL directly. Use the mcp-remote stdio bridge for static API keys, or open Settings -> Connectors -> Add custom connector for OAuth.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "nams-memory": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://memory.neo4jlabs.com/mcp",
        "--header",
        "Authorization:Bearer ${NAMS_API_KEY}"
      ],
      "env": {
        "NAMS_API_KEY": "nams_YOUR_API_KEY"
      }
    }
  }
}

Save, fully quit Claude Desktop (Cmd/Ctrl+Q), reopen it. The nams-memory server appears under the tools (hammer) icon. Ask: 'List the NAMS memory tools you have.'

Windows note: keep 'Authorization:Bearer' with no space -- mcp-remote arguments break on whitespace there.

Anthropic's CLI coding agent. Native streamable-HTTP MCP and OAuth discovery.

Run from any project directory:

claude mcp add --transport http --scope project nams \
  https://memory.neo4jlabs.com/mcp \
  --header "Authorization: Bearer nams_YOUR_API_KEY"

Start a session with `claude`, run `/mcp`, confirm `nams` is connected. Omit --header to use OAuth instead -- the first /mcp call opens a browser for PKCE.

OpenAI's terminal coding agent. Recent versions support remote streamable-HTTP MCP servers natively via TOML.

Edit ~/.codex/config.toml and add a server table.

[mcp_servers.nams]
url = "https://memory.neo4jlabs.com/mcp"
bearer_token_env_var = "NAMS_API_KEY"

Set NAMS_API_KEY in your shell, start a new Codex session, run `/mcp` to confirm `nams` is loaded. Older Codex installs are stdio-only -- wrap with `npx -y mcp-remote` instead.

Google's terminal coding agent. Use httpUrl (not url -- url silently routes through SSE, which this server does not expose).

Edit ~/.gemini/settings.json (or run `gemini mcp add -s user nams ...`):

{
  "mcpServers": {
    "nams": {
      "httpUrl": "https://memory.neo4jlabs.com/mcp",
      "headers": {
        "Authorization": "Bearer $NAMS_API_KEY"
      },
      "timeout": 5000
    }
  }
}

Set NAMS_API_KEY in your shell, restart any active Gemini session, run `/mcp`. Omit `headers` to trigger OAuth discovery on the server's 401 response.

GitHub's terminal coding agent. Native streamable-HTTP MCP -- add via `/mcp add` or edit the config file. Each server needs an explicit "type": "http".

Edit ~/.copilot/mcp-config.json:

{
  "mcpServers": {
    "nams": {
      "type": "http",
      "url": "https://memory.neo4jlabs.com/mcp",
      "headers": {
        "Authorization": "Bearer ${NAMS_API_KEY}"
      }
    }
  }
}

Set NAMS_API_KEY in your shell, run `/mcp` to confirm `nams` is listed (no restart needed). This is the standalone `copilot` CLI, not the older `gh copilot` extension.

AI code editor. Native streamable HTTP and OAuth discovery.

Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json (project root):

{
  "mcpServers": {
    "nams": {
      "url": "https://memory.neo4jlabs.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:NAMS_API_KEY}"
      }
    }
  }
}

Set NAMS_API_KEY in your shell, reload Cursor (Cmd/Ctrl+Shift+P -> Developer: Reload Window). Open Settings -> MCP and confirm `nams` is connected. Drop `headers` to use OAuth.

Codeium's Cascade-powered editor. Uses serverUrl (not url) for remote MCP endpoints.

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "nams": {
      "serverUrl": "https://memory.neo4jlabs.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:NAMS_API_KEY}"
      }
    }
  }
}

Set NAMS_API_KEY in your shell, reload Windsurf or hit Cascade -> MCP servers -> Refresh. Confirm `nams` is connected. Omit `headers` for OAuth.

The agentic terminal. Add via Settings -> AI -> MCP servers -> Add (Streamable HTTP / URL), not a CLI flag. A single server is a bare object -- no mcpServers wrapper.

Settings -> AI -> MCP servers -> Add -> Streamable HTTP or SSE Server (URL):

{
  "nams": {
    "url": "https://memory.neo4jlabs.com/mcp",
    "headers": {
      "Authorization": "Bearer nams_YOUR_API_KEY"
    }
  }
}

Warp sends header values verbatim -- paste your real key. Save, start the server from the same panel, then ask Agent Mode 'What memory tools do you have?'

After connecting, your agent will have access to all the NAMS memory, ontology, and workspace tools listed below. Each tool requires the scope shown in its row. An admin API key carries every scope, including workspace:admin; a workspace key (or OAuth login) carries only the data-plane scopes, so the workspace:admin tools are unavailable to it.

Tool	Description	Parameters	Required Scope
`memory_create_conversation`	Create a new conversation session for tracking agent interactions	user_id (optional)	`memory:write`
`memory_add_messages`	Add multiple messages to a conversation in bulk. Triggers async entity extraction.	conversation_id, messages (array of {role, content})	`memory:write`
`memory_get_context`	Get the three-tier context: reflections, observations, and recent messages	conversation_id	`memory:read`
`memory_search_messages`	Search messages within a conversation by content	conversation_id, query	`memory:read`
`memory_get_extraction_status`	Report entity-extraction status for a conversation's messages: per-message status (pending/processing/done/error), attempts, last run time, and a summary count by status.	conversation_id, workspace_id (optional)	`memory:read`

Tool	Description	Parameters	Required Scope
`memory_search_entities`	Search the knowledge graph for entities by name or type	query (optional), type (optional)	`entities:read`
`memory_get_entity`	Get details for a specific entity including its relationships	entity_id	`entities:read`
`memory_add_entity`	Add a new entity to the knowledge graph	name, type (person/organization/location/concept/tool/custom), description (optional)	`entities:write`
`memory_get_entity_history`	Get cross-conversation history - all messages that mention an entity	entity_id	`entities:read`
`memory_create_relation`	Create a typed relationship between two entities. Type is validated against the workspace's allowlist; unknown types collapse to RELATED_TO with the original name stored as a predicate property.	source_id, target_id, type, confidence (optional), workspace_id (optional)	`entities:write`
`memory_review_queue`	List pending entity-resolution SAME_AS pairs the resolver flagged as likely duplicates but didn't auto-merge - they need human review.	limit (optional, 1..100), workspace_id (optional)	`entities:read`
`memory_resolve_entity`	Apply a decision to a pending SAME_AS pair: 'confirm' merges source into target; 'reject' marks the pair as not-a-match.	source_id, target_id, action (confirm/reject), workspace_id (optional)	`entities:write`

Tool	Description	Parameters	Required Scope
`memory_record_step`	Record a reasoning step taken by an agent during a conversation	conversation_id, reasoning, action_taken, result (optional)	`reasoning:write`
`memory_record_tool_call`	Record a tool invocation made by an agent	tool_name, input, step_id (optional), output/status/duration_ms (optional)	`reasoning:write`
`memory_get_trace`	Get the full reasoning trace - all steps and tool calls	conversation_id	`reasoning:read`
`memory_explain_decision`	Get a detailed explanation of a reasoning step including tool calls and influenced entities	step_id	`reasoning:read`

Tool	Description	Parameters	Required Scope
`memory_ontology_list`	List ontologies in the workspace - system templates plus workspace-owned ontologies. The active one is flagged.	(none)	`ontology:read`
`memory_ontology_get`	Get one ontology (system or workspace-owned) and its full version history	id	`ontology:read`
`memory_ontology_get_active`	Get the workspace's active ontology version and parsed body (auto-binds nams-default if unbound)	(none)	`memory:read`
`memory_ontology_create`	Create a new workspace ontology with an initial revision (create-context-graph YAML shape)	name, body	`ontology:write`
`memory_ontology_update`	Update a workspace ontology - produces a new immutable revision. System templates are protected.	id, body	`ontology:write`
`memory_ontology_activate`	Switch the workspace's active ontology to a given version; future entity writes validate against it	id, version	`ontology:write`
`memory_ontology_clone`	Clone a system template into the workspace as an editable copy (fresh id, revision 1)	id	`ontology:write`
`memory_pending_types_list`	List pending entity types extraction proposed that the active ontology has not yet declared	ontology (optional)	`ontology:read`
`memory_pending_type_map`	Accept a pending entity type by mapping its surface form onto a declared entity-type label	surface_form, entity_type	`ontology:write`

Tool	Description	Parameters	Required Scope
`workspace_list`	List all workspaces the calling user is a member of	(none)	`workspace:admin`
`workspace_get`	Fetch a single workspace's details	workspace_id	`workspace:admin`
`workspace_create`	Create a workspace (idempotent by name). Managed sandbox or external Neo4j.	name, db_mode (managed/external), uri/database/username/password (external only)	`workspace:admin`
`workspace_update`	Update a workspace's metadata (currently rename)	workspace_id, name (optional)	`workspace:admin`
`workspace_delete`	Soft-delete a workspace; for managed workspaces, also stops the database	workspace_id	`workspace:admin`
`workspace_reprovision`	Replace a managed workspace's database with a fresh one, optionally restoring from a backup	workspace_id, restore_from_key (optional)	`workspace:admin`
`workspace_set_external_db`	Switch a workspace to an external Neo4j instance (e.g. Aura). Tests and initializes before persisting.	workspace_id, uri, database, username, password	`workspace:admin`
`workspace_get_database`	Get database connection info for a workspace - mode, URI, database, username (never the password)	workspace_id	`workspace:admin`
`workspace_list_backups`	List available database backups for a managed workspace (use a key as restore_from_key)	workspace_id	`workspace:admin`

Tool	Description	Parameters	Required Scope
`skill_generate`	Distill a scoped slice of workspace memory into a portable, provenance-grounded Agent Skill. Asynchronous: returns a runId to poll with skill_run_status.	scope_type (workspace/conversations/entity/ontology_class/time), conversation_ids/entity_id/ontology_class/from/to (per scope), name_hint/skill_id/procedure_format (optional)	`skills:write`
`skill_run_status`	Get the status and progress of a skill distillation run	run_id	`skills:read`
`skill_list`	List the distilled skills in a workspace with their latest-version summary	(none)	`skills:read`
`skill_get`	Get a skill's metadata, its rendered SKILL.md, and its version history	skill_id	`skills:read`
`skill_explain_provenance`	Explain why a skill recommends what it does: resolve each claim and procedure step to the source decisions, entities, and messages that grounded it	skill_id, version_id (optional)	`skills:read`
`skill_governance`	Audit the workspace's skill library as a graph (AIP corpus governance): ungrounded steps, skills missing a success-criteria component, shared sub-procedure reuse candidates, and the drifted set	(none)	`skills:read`
`skill_review`	Approve or reject the latest version of a skill (the human-review gate before publishing)	skill_id, decision (approve/reject), feedback (optional)	`skills:write`
`skill_publish`	Publish a skill's latest version. Requires the version to be review-approved; 409s if a called sub-procedure is unpublished.	skill_id	`skills:write`
`skill_execute`	Produce a guarded DRY-RUN execution plan for a published skill's procedure graph. Does NOT invoke any tool; gated by SKILL_EXECUTION_ENABLED with a default-deny tool allowlist.	skill_id, version_id (optional)	`skills:read`
`skill_extract_subprocedure`	Extract steps of a skill's served version into a new reusable sub-procedure skill, replacing them with a single CALLS step (AIP composition). Asynchronous: returns a runId to poll with skill_run_status.	skill_id, step_ids, name (optional)	`skills:write`
`skill_drift`	Report whether a skill has drifted from current memory (drift status, stale-claim count, last-checked time) as persisted by the periodic drift reconciler.	skill_id	`skills:read`
`skill_edit`	Validate a proposed edit to a skill's procedure graph against the graph invariants without mutating anything (dry run). Returns {valid, errors, steps}.	skill_id, ops (reorder/retype/edit_criterion/remove), version (optional)	`skills:write`
`skill_list_published`	List the workspace's published skills (discovery): name, served version, digest, procedure format, and whether the package is cryptographically attested.	(workspace-scoped)	`skills:read`

Label	Description
Conversation	A conversation session between an agent and user
Message	A single message within a conversation (user, assistant, or system)
Entity	A named entity in the knowledge graph (person, org, location, etc.)
AgentStep	A reasoning step recording the agent's thought process
ToolCall	A record of a tool invocation made during a reasoning step
Observation	A compressed summary generated from a window of messages
Reflection	A higher-level insight synthesized from multiple observations
Skill	A distilled, provenance-grounded Agent Skill (agentskills.io SKILL.md package). Lifecycle: draft, in_review, published, archived. Carries an extra :Subprocedure label when it is a called sub-procedure.
SkillVersion	An immutable version of a skill; holds rendered artifacts, the quality report, and procedureFormat ('graph' or 'prose')
SkillComponent	A content component of a skill version (kind: procedure, domain_model, exemplar, success_criteria, anti_pattern)
SkillStep	A typed step of the AIP Procedure Graph (kind: script, description, or call). A call step delegates to a sub-procedure Skill via CALLS.
DistillationRun	A record of a skill-distillation run (status: queued, snapshot_pinned, extracting, synthesizing, validating, packaging, succeeded, failed)

Type	From	To
`HAS_MESSAGE`	Conversation	Message
`HAS_STEP`	Conversation	AgentStep
`USED_TOOL`	AgentStep	ToolCall
`MENTIONS`	Message	Entity
`INFLUENCED`	AgentStep	Entity
`HAS_OBSERVATION`	Conversation	Observation
`HAS_REFLECTION`	Conversation	Reflection
`HAS_VERSION`	Skill	SkillVersion
`HAS_COMPONENT`	SkillVersion	SkillComponent
`HAS_STEP`	SkillVersion	SkillStep
`GROUNDED_IN`	SkillStep	AgentStep / ToolCall / Message / Entity / Observation / Reflection
`CALLS`	SkillStep	Skill
`DERIVED_BY`	SkillVersion	DistillationRun
`DISTILLED_FROM`	SkillVersion	AgentStep / ToolCall / Message / Entity / Observation / Reflection
`SUPERSEDES`	SkillVersion	SkillVersion

Type	Description
person	People, contacts, team members
organization	Companies, teams, groups
location	Cities, countries, addresses
concept	Ideas, topics, technologies
tool	Software tools, APIs, services
custom	User-defined entity types

Documentation

Get an API Key

REST: Make your first call

List entities

1. Create a conversation

2. Add a message

3. Check extracted entities

Connect your agent

Prefer OAuth 2.0?

Base URLs

Agent CLI plugins

Install

Configuration

Authentication

curl

Responses

curl

Responses

Request Body

curl

Responses

Parameters

curl

Responses

Parameters

curl

Responses

Parameters

curl

Responses

Parameters

curl

Responses

Request Body

curl

Responses

Request Body

curl

Responses

Short-Term Memory (Conversations)

Parameters

curl

Responses

Request Body

curl

Responses

Parameters

curl

Responses

Parameters

curl

Responses

Parameters

curl

Responses

Parameters

curl

Responses

Parameters

Request Body

curl

Responses

Parameters

Request Body

curl

Responses

Parameters

Request Body

curl

Responses

Long-Term Memory (Knowledge Graph)

Parameters

curl

Responses

Request Body

curl

Responses

curl

Responses

curl