Metadata-Version: 2.4
Name: aeeprotocol
Version: 8.0.0b1
Summary: Vector traceability with legal certification for AI embeddings
Home-page: https://github.com/ProtocoloAEE/aee-protocol
Author: Franco Luciano Carricondo
Author-email: francocarricondo@gmail.com
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Security :: Cryptography
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.21.0
Requires-Dist: scipy>=1.7.0
Requires-Dist: cryptography>=36.0.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# AEE Protocol v8
## Vector Traceability for the AI Era

**Protect your embeddings. Prove your ownership. Maintain compliance.**

AEE (Attribution & Evidence for Embeddings) is an open-source protocol for invisible watermarking of vector embeddings, with blockchain certification for legal proof. Survives 20% noise, <1% FP rate (10k tests).

### Quick Start
```python
pip install aeeprotocol  # DÃ­a 2

from aeeprotocol import AEEv8
aee = AEEv8(user_id=35664619)  # Tu DNI soberano

embedding = np.random.randn(768) / np.linalg.norm(np.random.randn(768))
marked, proof = aee.inject(embedding)
detection = aee.detect(marked)
print(f"Detected: {detection['detected']}, Confidence: {detection['confidence']}")
