Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready.
-
Updated
Mar 14, 2026 - Python
Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready.
Stop Claude Code from doing irreversible damage. Policy-gated execution + receipts so you can ship agents without sweating production.
Runtime guardrails for AI agents that enforce token budgets, loop limits, and tool rate limits locally.
Enforce token budgets, loop limits, and tool rate limits in AI agent runtimes to control execution and prevent resource overuse.
Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget enforcement, loop detection, kill switch. Zero dependencies, MIT licensed.
Add a description, image, and links to the runtime-guardrails topic page so that developers can more easily learn about it.
To associate your repository with the runtime-guardrails topic, visit your repo's landing page and select "manage topics."