Agent Safety Python Packages

tethered

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

langchain-sync-monitors

AI-control monitors for LangChain agents and Deep Agents: every step an agent proposes is judged before any of its own tools run, and a control protocol decides what runs.

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

nullrun

Enforcement gateway for AI agents. Nullrun official Python SDK.

agentguard47

Python runtime checks for AI agents: budgets, loops, retries, and local traces. Zero runtime dependencies. MIT.

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.

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.

yui-agent-guard

Static evidence contracts for AI-agent-maintained repositories.

wavemind

Verified experience for AI agents: independently checked, scoped, cited, and reversible.

interai-risk-oracle

Independent pre-execution decision layer for consequential agent actions. Policy-bound decisions with durable trust receipts.

agent-action-guard

🛡️ Safe AI Agents through Action Classifier

safeagent-exec-guard

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

agent-gorgon

Runtime policy guard for AI agent processes: watches process, file, and network activity from user space, applies deterministic policy, and attempts SIGSTOP or SIGKILL on reviewed triggers — no SDK required, works against any PID. Audit-only mode rehearses policy first; every decision logged as evidence.

sponsio

Deterministic safety solutions for probabilistic AI agents

quesen-sdk

Official Python SDK for Quesen — the deterministic AI decision engine for autonomous-agent risk evaluation.

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

crewscore

Find the safety rules your AI agent prompt forgot. Offline linter — 23 controls, CLI + Action + browser. No API key.

agents-never-sleep

Autonomous execution governance for coding agents: run a ticket backlog to completion unattended. ASK/PARK/HALT autonomy contract, durable per-ticket state machine, deterministic test gates, git-backed reversibility, heartbeat watchdog, morning report. Python stdlib only.

once-agent-sdk

Execution safety for side-effecting AI agent tools.

gate-cat

Block irreversible AI-agent actions before they run — deterministic, fail-closed action veto for Claude Code, Codex, Cursor, and other tool-using agents.

ekbasis

Ekbasis: an open world model for agents. What an action will do, before it is done.

yui-agent-policy

Pure-function policy matrix evaluator for AI coding agents (repo x capability x context -> deny/require_approval/auto_allow).

quesen-crewai

Official Quesen crewai integration — deterministic A2A risk validation.

quesen-langchain

Official Quesen langchain integration — deterministic A2A risk validation.