Tag: #safety
10 packages âĸ â 6,694 total stars
An open-source SDK for AI agent safety
Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.
Self-evolving AI agent framework with 5-layer safety gatekeeper. Agents observe failures, propose fixes, and safely apply them. Built on HKUDS/nanobot.
A guardrail system that intercepts and validates AI agent tool calls
AI Agent Safety Monitor with LLM-based Command Safeguard
Agent Integrity Protocol â real-time thinking block analysis for AI agent alignment
Framework-agnostic Petri net gating for AI agent tool access control. Define safety constraints as Petri nets â tools are only allowed when an enabled transition permits them.
AI Agent Governance CLI â evaluate tool calls against rules, block dangerous operations, and surface blocked commands
Runtime rule enforcement for AI agent tool calls