Agent Safety Python Packages

tethered

Runtime network egress control for Python

xsafeclaw

XSafeClaw - Keeping Your Claw Safe. Real-time monitoring and security for OpenClaw, Hermes, and nanobot AI agents.

armorer-guard

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

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.

langchain-runcycles

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

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.

shadowaudit

Runtime governance for AI agents — deterministic fail-closed enforcement. Wraps any agent tool and blocks dangerous calls before execution. Zero LLM calls, zero cloud dependencies, works offline.

agent-action-guard

🛡️ Safe AI Agents through Action Classifier

jamjet

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

runcycles

Python SDK for Cycles — reserve, commit, release budget and risk for AI agents

capfence

Runtime governance for AI agents — deterministic fail-closed enforcement. Wraps any agent tool and blocks dangerous calls before execution. Zero LLM calls, zero cloud dependencies, works offline.

mcp-rampart

Security toolkit for FastAPI-based MCP servers — pre-flight audit + runtime prompt-injection guardrail. 97M MCP installs/month — someone has to audit what they expose.

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.

agsec

An action firewall for AI agents. Before an agent can do anything in the real world, it must pass through agsec.

proofflow-mcp

MCP server for ProofFlow – audit infrastructure for AI coding agents

safeagent-exec-guard

AI agent execution guard — prevents duplicate actions from retries with exactly-once execution, request-id dedup, and durable receipts.

agentguardx

Runtime security layer for AI agents — inspect, control, and audit every tool call. Trust-aware data flow, 3-layer intent consistency detection, Merkle audit trail. Drop-in support for LangChain, CrewAI, AutoGen, OpenClaw, MCP, Dify, AutoGPT, n8n.

magicrails

🛑 Emergency brake for AI agents. Hard budget caps, loop detection, and state-stasis guards in 3 lines of Python. Stops runaway agents before the $500 overnight invoice.

sponsio

Deterministic safety solutions for probabilistic AI agents

shannot

Human-in-the-loop execution for LLM agents

runcycles-openai-agents

Runtime budget, action, and audit authority for the OpenAI Agents SDK — enforce LLM cost limits, tool call caps, and audit trails before execution.

agent-safety-mcp

MCP server for AI agent safety — cost guards, injection scanning, decision tracing, agent identity (KYA), and signed receipts

jadegate

💠 The security scanner for AI agents. 5-layer verification for MCP servers & skills. Zero dependencies.

fivedrisk

Per-action AI agent risk scoring and governance. Deterministic 5D scoring, HITL gating, FinOps, Agent Cost Management, Markov drift, audit log. Apache-2.0.