Skip to main content

CMVK — Verification Kernel — Public Preview

Part of Agent OS - Kernel-level governance for AI agents

PyPI version License: MIT

Basic drift detection between model outputs.

CMVK provides lightweight functions for comparing text and embeddings to detect when model outputs diverge. Use it to verify that two models (or two runs of the same model) produce semantically equivalent results.

Installation

pip install agentmesh-drift

Quick Start

from cmvk import verify

score = verify("def add(a, b): return a + b", "def add(x, y): return x + y")
print(f"Drift: {score.drift_score:.3f}")  # 0.0 = identical

Features

  • Text comparison with drift scoring (0.0–1.0)
  • Embedding and distribution comparison utilities
  • Batch verification with aggregation
  • Zero external service dependencies (numpy only)

License

MIT License - see LICENSE for details.

Metadata

Release files for agentmesh_drift 3.7.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agentmesh_drift 3.7.0
File Size Uploaded Provenance
agentmesh_drift-3.7.0.tar.gz 34.9 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for agentmesh_drift 3.7.0
File Interpreter ABI Platform
agentmesh_drift-3.7.0-py3-none-any.whl Python 3 none any Details

Total release size: 73.6 kB

Release files / agentmesh_drift-3.7.0.tar.gz

Download URL agentmesh_drift-3.7.0.tar.gz
Size 34.9 kB
Tags Source
SHA-256 checksum
How to use checksums
a35db6c4764a3cdbcc719bd087ab61053488687241815c6bc96b1ef466658e59
BLAKE2b-256 checksum
How to use checksums
a03e726280973804d52402d95fc27a0854a8c08c16c382076053454012968dbb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via RestSharp/106.13.0.0

Release files / agentmesh_drift-3.7.0-py3-none-any.whl

Download URL agentmesh_drift-3.7.0-py3-none-any.whl
Size 38.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
de7305dbc12ce8b0a98fbac685cead7d0e520afc285aefdbabda870f1bcf26d8
BLAKE2b-256 checksum
How to use checksums
eca95898cd715717b811fecbd3fca3486987c083f1def51609752b18588aca48
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via RestSharp/106.13.0.0

Security for agentmesh_drift 3.7.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page