Matriosha is a Python CLI for an encrypted, auditable AI context engine.
Project description
Matriosha
Matriosha is a Python CLI for an encrypted, auditable AI context engine.
Hold AI accountable. Own your data.
Install
Matriosha supports Python 3.11, 3.12, 3.13, and 3.14.
pip install matriosha
Quickstart
Initialize an encrypted local vault:
matriosha vault init
Remember text:
matriosha memory remember "Important launch context" --tag launch
Remember a file:
matriosha memory remember --file ~/Documents/agent-notes/launch-context.md
Search semantically:
matriosha memory search "What is the launch motto?"
Verify vault integrity:
matriosha vault verify
Why Matriosha?
AI agents are gaining longer memories, but many memory systems are opaque, vendor-bound, or difficult to verify.
Matriosha keeps AI context outside the model provider and makes it:
- Encrypted: vault data is protected with modern cryptography.
- Auditable: local audit events and vault integrity can be verified.
- Model-agnostic: memory is not tied to one AI vendor.
- Local-first: start offline, then opt into managed workflows when needed.
Local and managed modes
Local mode is free, offline-first, and does not require authentication.
Managed mode is designed for cloud-backed operational workflows such as sync, policy, quota, billing, token workflows, and agent workflows.
Requirements
- Python
>=3.11,<3.15 - A Unix-like shell for the examples, such as Terminal on macOS, Linux shells, or WSL/Git Bash on Windows
Core commands
matriosha vault init
matriosha memory remember "hello from local mode" --tag demo
matriosha memory search "hello"
matriosha audit verify
matriosha vault verify
matriosha vault verify --deep
matriosha token generate my-agent --local --expires-in 30d
matriosha agent connect --local --name my-agent --kind desktop --token <token>
matriosha agent list --local
Security model
- Argon2id passphrase hardening
- AES-256-GCM authenticated encryption
- SHA-256 and Merkle-root integrity checks
- Local audit verification
- Ed25519 signature-ready workflows
Project links
- Homepage: https://github.com/drizzoai-afk/matriosha
- Issues: https://github.com/drizzoai-afk/matriosha/issues
- License: BSD 3-Clause
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file matriosha-2.0.1.tar.gz.
File metadata
- Download URL: matriosha-2.0.1.tar.gz
- Upload date:
- Size: 149.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2a8812df4885efc6023f496f310d0eb4fd9c28fd1d147c81cca089f21e85ab3f
|
|
| MD5 |
866ef8d1d0cc318ea979eafea700aec9
|
|
| BLAKE2b-256 |
3bf47c22e101cda03d2aaa0d7503a6abcd9accc949e91f355773aa3762905ef6
|
File details
Details for the file matriosha-2.0.1-py3-none-any.whl.
File metadata
- Download URL: matriosha-2.0.1-py3-none-any.whl
- Upload date:
- Size: 207.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d4d1a97092598b3d3409d0008f0f6f982ee65fd1d13cc487b002502ed961f73f
|
|
| MD5 |
2dbaed135b9393be5eda07c417aef9db
|
|
| BLAKE2b-256 |
441e498a4872219de1f7b67e587cd26caba663d6a4537afc61ab8fcb72cac62b
|