PyPI page
Home page
Author:
Dmitry Krivonosov
Summary:
Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests.
Latest version:
1.14.1
Required dependencies:
pydantic
Optional dependencies:
agentic-llm-router
|
agentic-transfer-verifier
|
agentic-transfer-verifier-harness-extension
|
ai-agent-handoff
|
ai-agent-handoff-harness-extension
|
llm-cheap-filter
|
llm-safety-playbooks
|
mypy
|
pydantic-ai-slim
|
pytest
|
ruff
Downloads last day:
28
Downloads last week:
609
Downloads last month:
1,494
7-day smoothing