Search Packages

xsafeclaw

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

tethered

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

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.

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.

agent-action-guard

🛡️ Safe AI Agents through Action Classifier

runcycles

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

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.

agsec

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

curiosity-cat

A safety framework for AI agents that explore the internet. Standing orders, crowdsourced threat intelligence, and real close-call stories.

safeagent-exec-guard

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

sponsio

Deterministic safety solutions for probabilistic AI agents

shannot

Human-in-the-loop execution for LLM agents

jadegate

Deterministic Security for AI Agent Skills — 151 verified skills with Ed25519 signature chain

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.

agentshield-runtime

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.

agentshield-fw

The runtime firewall for AI agents. Protect any agent in 3 lines of code.

agent-safety-mcp

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

ai-decision-tracer

Zero-dependency AI agent decision tracer. Records every step — what it saw, decided, and why. JSON + Markdown output.

csc-runner

Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.

mcp-security-audit

MCP Security Auditor — scan any MCP server for injection patterns, risky tools, and misconfigurations

kya-agent

Know Your Agent — An open standard for AI agent identity, compliance, and auditability

suy-sideguy

Runtime policy guard for autonomous AI agents with user-space enforcement and forensic reporting

agentic-contract

Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation tracking, and violation detection. One .acon file. Rust core + MCP server.

agentcred

Agent Credit Bureau — trust scoring and audit reports for AI agents and MCP servers