Skip to main content

ApertoMemory — portable, client-side-encrypted, user-owned AI memory

Project description

ApertoMemory

Memoria AI portabile, cifrata lato client, di proprietà dell'utente.

Installa con pip install apertomemory — il comando da terminale è amem, il formato file è .amem. Sito: https://apertomemory.org

export AMEM_PASSPHRASE="la-tua-passphrase"
amem --vault ~/.amem init
amem --vault ~/.amem scope add default
amem --vault ~/.amem seal "preferisce email B2B formali" --tags preferences
amem --vault ~/.amem open <id>
amem --vault ~/.amem export mia-memoria.amem     # portala dove vuoi
amem --vault altro-device import mia-memoria.amem

Crittografia (spec §4-§6): Argon2id (m=64MiB, t=3, p=4) → HKDF-SHA256 → Ed25519 (firma, sign-then-encrypt) + X25519 (ECDH-ES + AES-KW per le KEK di scope) → AES-256-GCM per oggetto (COSE alg 3), CBOR canonico RFC 8949 §4.2. Il vault e il file .amem non contengono mai chiavi o contenuti in chiaro.

Test: python3 tests/test_roundtrip.py

Adapter MCP (Claude Desktop / Claude Code)

{
  "mcpServers": {
    "amem": {
      "command": "python3",
      "args": ["-m", "amem.mcp_server"],
      "env": {"AMEM_VAULT": "/percorso/vault", "AMEM_PASSPHRASE": "la-tua-passphrase"}
    }
  }
}

Tool esposti: amem_remember, amem_recall, amem_export, amem_import, amem_status. La passphrase vive solo nell'ambiente locale: il modello non la vede mai. Demo "nuovo device": amem_export → sposti il file .amemamem_import su un vault vergine → amem_recall e l'AI ti conosce già.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

apertomemory-0.1.1.tar.gz (10.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

apertomemory-0.1.1-py3-none-any.whl (11.7 kB view details)

Uploaded Python 3

File details

Details for the file apertomemory-0.1.1.tar.gz.

File metadata

  • Download URL: apertomemory-0.1.1.tar.gz
  • Upload date:
  • Size: 10.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.5

File hashes

Hashes for apertomemory-0.1.1.tar.gz
Algorithm Hash digest
SHA256 aa89ced5641ffee7139716f2a7859060c45dc7d2a06cb8c5a4ba4fc371ee0ced
MD5 023ca9ea558349cd3eba647479a7d1b4
BLAKE2b-256 f0443086d80b9f12ebe8031e6264eb343902354f123339f94072b5e2c9a691c7

See more details on using hashes here.

File details

Details for the file apertomemory-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: apertomemory-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 11.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.5

File hashes

Hashes for apertomemory-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0815ea1e251b06e5a9090e7874cd49019f87f54c0c4ae6838753c439c1b4cbb9
MD5 b941f0351a78040f890fd1dbe3dc9005
BLAKE2b-256 b87b70b053a6b1c20ac364f4059416e63bd07a8ccdb432ccd925b3e1d0ddb05b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page