Agent Architecture Python Packages

dof-sdk

Deterministic Observability Framework — formal governance, privacy benchmarks, and adversarial testing for multi-agent LLM systems

agchk

Audit the architecture and health of any AI agent system or LLM-integrated project

icm-workspace-template

Reusable Interpretable Context Methodology (ICM) workspace template for filesystem-based AI agent workflows

mcp-agent-runtime

Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.

soveryn-cathedral

Continuous identity layer for single-user sovereign AI — working memory and self-state across surfaces. Schema co-authored by the agent it serves.