Migrate - MemoClaw

curl -X POST https://api.memoclaw.com/v1/migrate \
  -H "Content-Type: application/json" \
  -d '{
    "files": [
      {
        "filename": "2026-01-30.md",
        "content": "## Project Setup\nDecided to use PostgreSQL with pgvector.\n\n## Config\nUser prefers dark mode."
      }
    ]
  }'

{
  "files_processed": 1,
  "memories_created": 2,
  "memories_deduplicated": 0
}

POST

migrate

curl -X POST https://api.memoclaw.com/v1/migrate \
  -H "Content-Type: application/json" \
  -d '{
    "files": [
      {
        "filename": "2026-01-30.md",
        "content": "## Project Setup\nDecided to use PostgreSQL with pgvector.\n\n## Config\nUser prefers dark mode."
      }
    ]
  }'

{
  "files_processed": 1,
  "memories_created": 2,
  "memories_deduplicated": 0
}

Parses markdown files, splits by ## headers, auto-detects importance and memory type, and stores each section as a separate memory. Idempotent — duplicate content is deduplicated via content hashing.

Request Body

files

array

required

Array of file objects to import. Maximum 50 files per request.

Show File object

filename

string

required

Original filename (e.g., 2026-01-30.md). Dates in YYYY-MM-DD format are extracted and added as tags.

content

string

required

Raw markdown content of the file.

Response

files_processed

integer

Number of files successfully processed.

memories_created

integer

Number of new memories stored.

memories_deduplicated

integer

Number of memories skipped due to duplicate content.

errors

array

Present only if some files failed. Each entry has filename and error.

curl -X POST https://api.memoclaw.com/v1/migrate \
  -H "Content-Type: application/json" \
  -d '{
    "files": [
      {
        "filename": "2026-01-30.md",
        "content": "## Project Setup\nDecided to use PostgreSQL with pgvector.\n\n## Config\nUser prefers dark mode."
      }
    ]
  }'

{
  "files_processed": 1,
  "memories_created": 2,
  "memories_deduplicated": 0
}

How parsing works

Each file is split on ## headers
Each section becomes one memory with:
- content: header + body text (max 8,000 chars)
- importance: 0.6–0.9 based on keyword heuristics (decisions=0.9, preferences=0.8, etc.)
- memory_type: auto-detected (decision, preference, correction, project, observation, general)
- tags: header words + date:YYYY-MM-DD from filename + migrated + openclaw
Content is SHA-256 hashed for intra-batch and cross-request deduplication
Files without ## headers are stored as a single memory

Pricing

Endpoint	Cost
`POST /v1/migrate`	$0.01 per request

Delete Memories Memory History

​Request Body

​Response

​How parsing works

​Pricing

Request Body

Response

How parsing works

Pricing