Agent Safety Python Packages

yui-agent-guard

Static repository guardrails for agent-touched codebases.

tethered

tethered — Runtime network egress control for Python. One function call to restrict which hosts your code can connect to.

arbiter-client

Arbiter: A capability firewall between AI agents and services

jamjet

The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.

actra

Actra - control what runs before it runs, controls what actions are allowed before they execute. Evaluate policies across APIs, workflows and AI agents in real time.

armorer-guard

Fast local Rust scanner for AI-agent prompt injection, credential leaks, exfiltration, and risky tool calls

arbiter-server

Arbiter: A capability firewall between AI agents and services

safeagent-exec-guard

Execution control layer for AI agents — prevents duplicate or incorrect real-world actions under retries, uncertainty, and stale context.

arbiter-imap

Arbiter: A capability firewall between AI agents and services

xsafeclaw

Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

ethicore-engine-selfhost

Ethicore Engine™ is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

ethicore-engine-guardian

Ethicore Engine™ is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

arbiter-smtp

Arbiter: A capability firewall between AI agents and services

intaris

Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.

agentguard47

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.

arbiter-suite

Arbiter: A capability firewall between AI agents and services

sponsio

Deterministic safety solutions for probabilistic AI agents

state-harness

Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness

agent-action-guard

Runtime classifier for screening AI agent actions as safe, harmful, or unethical.

arbiter-skill

Arbiter: A capability firewall between AI agents and services

precheck-guardian

A pre-execution approval gate for AI agents: preview the plan, see per-step risk, approve/reject/edit before anything runs. Framework-agnostic, zero core deps.

langchain-runcycles

LangChain agent middleware for Cycles — pre-tool-call authorization and per-tenant budget enforcement for Python agents using create_agent

shannot

Human-in-the-loop execution for LLM agents

agsec

AI Agent Action Firewall core SDK