Quick Start

1. Install the PAM SDK

pip install 'portable-ai-memory[cli]'

2. Create a minimal memory store

Save this as memory-store.json:

{
  "schema": "portable-ai-memory",
  "schema_version": "1.0",
  "export_date": "2026-02-17T00:00:00Z",
  "owner": {
    "id": "user-123"
  },
  "memories": [
    {
      "id": "mem-001",
      "type": "skill",
      "content": "User is a cloud infrastructure engineer",
      "content_hash": "sha256:e1bae3ec291c99eced01fc91b4152a0cef541fccf2034fc11b3f90f4e4d79b6e",
      "temporal": {
        "created_at": "2026-02-15T00:00:00Z"
      },
      "provenance": {
        "platform": "chatgpt"
      }
    }
  ]
}

3. Validate

CLI — the fastest path:

pam validate memory-store.json

Python — for programmatic validation:

from portable_ai_memory import load, validate_memory_store

store = load("memory-store.json")
result = validate_memory_store(store)

if result.is_valid:
    print(f"Valid — {len(store.memories)} memories")
else:
    for issue in result.errors:
        print(issue)

If the file is valid, you’ll see:

✓ All checks passed

That’s it — you have a valid PAM file. See Examples for more complex scenarios, or read the full Specification.

---

Validating without the SDK

If you can’t use Python, you can validate against the JSON Schemas directly with any JSON Schema Draft 2020-12 validator. See the Validation Guide for jsonschema (Python) and ajv (Node.js) examples.

Note that manual validation only checks schema compliance — it does not verify content hashes, cross-references, or temporal consistency.