Guardrail agents

An open-source SDK for AI agent safety

Authensor guardrail adapter for LangChain/LangGraph

Framework-agnostic agent loop detection — sliding window similarity scoring to catch stuck agents

APort Agent Guardrail — shared core for AI agent and LLM frameworks (pre-action authorization)

APort Agent Guardrail for CrewAI — before_tool_call hook for AI agent and multi-agent crews

APort Agent Guardrail for LangChain/LangGraph — AsyncCallbackHandler for AI agent tool calls

EYDII Verify tools and guardrails for CrewAI — verify every agent action before execution

Forge Verify + Execute tools and guardrails for CrewAI — verify agent actions and track executions with…

EYDII Verify guardrail for OpenAI Agents SDK — verify every tool call before execution

Forge Verify + Execute middleware for OpenAI Agents SDK — verify tool calls and track executions with…

Strict JSON LLM outputs with multi-provider support (Anthropic / OpenAI / DeepSeek / Kimi / Google)

EYDII Verify middleware for LangGraph/LangChain — verify every tool call before execution

Forge Verify + Execute middleware for LangGraph/LangChain — verify tool calls and track executions with…

EYDII Verify tools for LlamaIndex — verify every agent action before execution

Forge Verify + Execute tools for LlamaIndex — verify agent actions and track executions with cryptographic…

Model-agnostic LLM output degeneration detector — 4-signal composite scoring in a single pass

AI safety guardrail — intent analysis, prompt injection detection, and policy enforcement for LLM applications

A lightweight Python guardrail SDK for content safety

Portable, stdlib-only guardrail for autonomous coding agents — safe continuations instead of reckless actions.

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude…

llama-index Bastion Prompt Protection guardrail integration