Skip to main content
POST
/
api
/
v2
/
agents
/
{agent_id}
/
remember
curl -X POST "http://localhost:8000/api/v2/agents/my-agent/remember" \
  -H "X-Session-Token: your_session_token" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "User prefers email communication",
    "type": "preference",
    "confidence": 0.9,
    "tags": ["communication"],
    "source": "agent",
    "provenance": "explicit_statement"
  }'

{
  "memory_id": "b7c3cf31-e537-49f1-abc4-c50ac6adeac5",
  "agent_id": "my-agent",
  "session_id": "9f733fdb-ebf2-494e-8eb6-fb3320d6020d",
  "namespace": "memanto_agent_my-agent",
  "status": "queued",
  "confidence": 0.9,
  "provenance": "explicit_statement"
}

​
Overview

Stores one memory in the agent’s Moorcheh namespace scoped by the active session. Fields are sent as JSON in the request body only (no query-string parameters).

​
Authentication

API clients do not send an API key or Authorization header.
​
X-Session-Token
string
required
Session token from Activate Agent. Must match agent_id.
​
Content-Type
string
required
Must be application/json

​
Path Parameters

​
agent_id
string
required
The unique identifier of the agent.

​
Body

​
content
string
required
Memory text to store (max length enforced by the server; typically up to 10,000 characters).
​
type
string
default:"fact"
Memory category (e.g. fact, preference, instruction, decision, goal, …). Must be one of the supported Memanto memory types.
​
title
string
Optional title (max 100 characters). If omitted, a title is derived from the content.
​
confidence
number
default:"0.8"
Confidence between 0.0 and 1.0.
​
tags
array
Optional list of tag strings.
​
source
string
default:"agent"
Source label for the memory (e.g. agent, user).
​
provenance
string
default:"explicit_statement"
How the memory was obtained: explicit_statement, inferred, observed, validated, corrected, imported.
curl -X POST "http://localhost:8000/api/v2/agents/my-agent/remember" \
  -H "X-Session-Token: your_session_token" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "User prefers email communication",
    "type": "preference",
    "confidence": 0.9,
    "tags": ["communication"],
    "source": "agent",
    "provenance": "explicit_statement"
  }'

{
  "memory_id": "b7c3cf31-e537-49f1-abc4-c50ac6adeac5",
  "agent_id": "my-agent",
  "session_id": "9f733fdb-ebf2-494e-8eb6-fb3320d6020d",
  "namespace": "memanto_agent_my-agent",
  "status": "queued",
  "confidence": 0.9,
  "provenance": "explicit_statement"
}

​
Next Steps