Provenize — Audit-grade memory infrastructure for AI agents (development in progress)
Project description
Provenize
Audit-grade memory infrastructure for AI agents in regulated industries.
Status
🚧 Currently under active development. This package is a name reservation placeholder. The full Provenize SDK will be published in late 2026.
This placeholder exists to:
- Reserve the
provenizename on PyPI - Provide a stable installation target for early documentation
- Signal active development to the open-source community
What is Provenize?
Provenize is an open-source Python SDK that provides audit-grade memory infrastructure for AI agents operating in regulated industries. It is designed specifically for:
- Pentest firms — engagement-scoped memory with cryptographic audit trails for security work
- Law firms — matter-scoped memory with full citation chains for legal AI use cases
- Banking compliance teams — TIBER-EU compatible AI memory layer with regulatory reporting
- Regulated industries generally — GDPR Article 17 erasure, hash- chained audit logs, local-first deployment
Planned Features (v1.0)
Coming in late 2026:
- Hash-chained audit logs — cryptographically verifiable trail of every AI memory operation
- GDPR Article 17 erasure — HMAC-with-key-deletion implementation that proves erasure occurred
- Local-first deployment — no client data leaves operator infrastructure
- MCP server integration — works with Claude Code, Hermes-Agent, and other MCP-compatible AI platforms
- Domain profiles — pre-configured for security, legal, medical, and financial verticals
- Multi-user PostgreSQL backend — for team and enterprise tiers
Why Apache 2.0?
The Apache 2.0 license provides:
- Patent protection that MIT and BSD do not
- Enterprise-friendly terms for procurement
- Compatibility with most open-source ecosystems
- The standard license for cybersecurity open-source tooling
Project Status
| Current version | 0.0.1 (name reservation placeholder) |
| Target v1.0 | Q4 2026 |
| Current phase | Internal development (Phase 4) |
| License | Apache 2.0 |
| Python support | 3.10+ |
Links
- Homepage: https://provenize.ai
- Documentation: Coming with v1.0
- Source code: Coming with v1.0
- Contact: info@provenize.ai
Installation (Placeholder)
pip install provenize
The current version (0.0.1) provides no functional API. It exists for name reservation only. Installation is safe but does nothing useful yet.
import provenize
provenize.info()
# Prints development status and links to provenize.ai
License
Apache License 2.0 — see LICENSE when released.
Copyright © 2026 Provenize. All rights reserved.
This placeholder package was created on 2026-05-14 to reserve the "provenize" name on PyPI ahead of the v1.0 release.
Project details
Release history Release notifications | RSS feed
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 provenize-0.0.1.tar.gz.
File metadata
- Download URL: provenize-0.0.1.tar.gz
- Upload date:
- Size: 7.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ee951226aba3e0363bca83c3f8a9614cd10cd2a64656c453630bd387794dc069
|
|
| MD5 |
79b95c624affecab74445304ac86bbbd
|
|
| BLAKE2b-256 |
b0f7d038c4b9cbff5f6904ff868e14ef50a9ecf357d1205c06c7d2bf815b5cff
|
File details
Details for the file provenize-0.0.1-py3-none-any.whl.
File metadata
- Download URL: provenize-0.0.1-py3-none-any.whl
- Upload date:
- Size: 7.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
67c5c2e427152d7a10f472d5aac0a2067a1809a6cae24024208a2827909e6719
|
|
| MD5 |
8bc518b2a29b77be57247883eb5fdcaa
|
|
| BLAKE2b-256 |
ec2aaf495a9e6dbb346b578264f7bd9c6bc1244f1d4c48db1385b61079cf05de
|