Skip to main content
POST
/
v1
/
context
Assemble Context
curl --request POST \
  --url https://api.memoclaw.com/v1/context \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "namespace": "<string>",
  "session_id": "<string>",
  "agent_id": "<string>",
  "max_memories": 123,
  "max_tokens": 123,
  "format": "<string>",
  "include_metadata": true,
  "summarize": true
}
'
{
  "context": "<string>",
  "memories_used": 123,
  "tokens": 123
}

Documentation Index

Fetch the complete documentation index at: https://docs.memoclaw.com/llms.txt

Use this file to discover all available pages before exploring further.

This endpoint requires an x402 payment header.
Price: $0.01 USDC Automatically assemble relevant memories into a context block ready for LLM prompts. This is useful for building AI assistants that need contextual memory.

​
Request Body

​
query
string
Natural language query describing what context is needed. Used to find relevant memories.
​
namespace
string
Filter by namespace.
​
session_id
string
Filter by session ID.
​
agent_id
string
Filter by agent ID.
​
max_memories
number
Maximum number of memories to include. Default: 10. Max: 100.
​
max_tokens
number
Target maximum tokens for the context. Default: 4000. Range: 100-16000.
​
format
string
Output format: text (plain text) or structured (JSON with metadata). Default: text.
​
include_metadata
boolean
Include memory metadata (tags, importance, type) in the output. Default: false.
​
summarize
boolean
Use LLM to summarize multiple similar memories into fewer entries. Default: false.

​
Response (200 OK)

​
context
string
The assembled context text or JSON.
​
memories_used
number
Number of memories included in the context.
​
tokens
number
Approximate token count of the context.

​
Example

curl -X POST https://api.memoclaw.com/v1/context \
  -H "Content-Type: application/json" \
  -d '{
    "query": "user preferences and project context",
    "max_memories": 5,
    "max_tokens": 2000,
    "format": "text"
  }'
Response
{
  "context": "User preferences:\n- Prefers dark mode\n- Uses vim keybindings\n- Timezone: PST\n\nProject context:\n- Using PostgreSQL 15 with pgvector\n- Deploy to staging before production",
  "memories_used": 5,
  "tokens": 180
}
Response (structured format)
{
  "context": {
    "memories": [
      {
        "content": "User prefers dark mode",
        "importance": 0.8,
        "memory_type": "preference",
        "tags": ["ui"],
        "source": "recall"
      },
      {
        "content": "Uses vim keybindings",
        "importance": 0.7,
        "memory_type": "preference",
        "tags": ["editor"],
        "source": "recall"
      }
    ]
  },
  "memories_used": 2,
  "tokens": 85
}