Runtime guardrails for AI agents that enforce token budgets, loop limits, and tool rate limits locally.

Teams and Solo Devs Claude Code hooks setup for observability and guardrails. Understand how skill, subagents, prompts are working and where is claude struggling to improve systematically

Deterministic governance engine for AI agents. Enforce rules defined in .md governance files across AI systems.

Human-readable approval guard for AI coding agents. shzx intercepts shell commands, explains them in plain English, and shows risk levels before you execute it.

Security kernel + sandboxed runner for AI agents

Who watches the agents?

On-chain guardrails for AI agents — EIP-7702 spend limits, cryptographic execution receipts, automated dispute resolution. No agent should hold unguarded keys.