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.
Prove every scheduled machine is still alive — a registry plus a verifier that catches silently dead cron jobs, agent runs, and timers, and drift in both directions. A checker that never fires is indistinguishable from a healthy system.
A curated list of tools and prior art for governed agents — approval gates, policy boundaries, decision records, and rollback for autonomous systems.
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."