Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictable tool steps.
-
Updated
Mar 9, 2026 - Python
Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictable tool steps.
Holdout scenario evaluation harness for AI agents. Doer/Judge/Adversary/Observer roles, probabilistic satisfaction scoring, append-only JSONL audit trails with integrity hashes. Created Dec 2025.
Umbrella repo: orchestration + documentation for the agent suite.
Add a description, image, and links to the deterministic-agents topic page so that developers can more easily learn about it.
To associate your repository with the deterministic-agents topic, visit your repo's landing page and select "manage topics."