Catalog PyPI
PACKAGE EXPLORERView in registry

agentmesh_drift

PyPI

Mathematical drift detection library for calculating drift/hallucination scores between outputs

adversarialai-safetydrift-detectionhallucinationmathematicalscoringverification
Versions collected1
Direct dependencies8From release 3.7.0
Last observed20 Oct, 22:42 UTC

README

Version 3.7.0 documentation

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.

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases
VersionPublishedDirect dependenciesOpen version
3.7.018 May 20268

Package advisories

0
No matching advisories collected

This describes our collected data; it is not a security assessment.

Repository

PENDING
microsoft/agent-governance-toolkit

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 22:42 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:1c4c2280d7497cbdb46a8000365dc36a2088311f4ff012932470db1707ed0557