Current collected state Current
Observed since 20 Oct, 22:42 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
Mathematical drift detection library for calculating drift/hallucination scores between outputs
Part of Agent OS - Kernel-level governance for AI agents
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.
pip install agentmesh-drift
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
MIT License - see LICENSE for details.
Download counts and popularity will appear here as the collector receives them.
| Version | Published | Direct dependencies | Open version |
|---|---|---|---|
| 3.7.0 | 18 May 2026 | 8 |
This describes our collected data; it is not a security assessment.
Shared repository data · GitHub
Observed since 20 Oct, 22:42 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package:1c4c2280d7497cbdb46a8000365dc36a2088311f4ff012932470db1707ed0557