GoPlus AgentGuard — Security guard for AI agents. Blocks dangerous commands, prevents data leaks, protects secrets. 20 detection rules, runtime action evaluation, trust registry.

All terminology and labels used in AgentGuard materials are descriptive of software functionality only, not legal definitions or guarantees of compliance. Terms like receipt, audit log, evidence, audit trail, and attestation refer solely to cryptographica

AgentGuard TypeScript SDK with local policy contracts and compatibility HTTP/in-process adapters.

AgentGuard CLI — scan agent source code and validate policy coverage

AgentGuard MCP server: local spend caps, kill-switch style blocking, and Ed25519-signed provenance receipts for AI agent actions. Zero data plane: prompts never pass through this server.

AppOmni's AgentGuard node

MCP server for agentguard: declarative network-egress firewall for agent tools. Check whether a URL is allowed under a policy before any fetch.

AgentGuard security hooks for OpenClaw

Official JavaScript/TypeScript SDK for AgentGuard AI authorization service

Policy engine behind agentguard: spend caps, destructive-action gating with approvals, kill switch, scoped agent keys, dry-run writes, semantic loop breaker, blast-radius caps and a hash-chained audit log. Web-standard core, Node stores under ./node.

AgentGuard SDK for JavaScript/TypeScript - Monitor and protect your AI agents

AgentGuard: policy enforcement in front of an autonomous on-chain agent. An agent cannot widen the limits its operator set.

Agent Guard observability and guardrails SDK for Node.js

agentguard for tool calls that bypass MCP: wrap OpenAI Agents SDK, LangChain or plain function tools with the same policy engine (spend caps, approvals, kill switch, dry-run, loop breaker, audit log) and cap LLM spend with a guarded fetch.

AgentGuard security monitoring plugin for OpenClaw

Local session usage and runaway-agent circuit breaker. Explain tokens, cache rewrites and API list cost, track pace, warn on heavy turns, and gate agent fan-out with signed receipts. Nothing leaves the machine.

AgentGuard security monitoring hook for Claude Code

MCP policy proxy for AI agents: hard spend limits, destructive-action gating with approvals, a kill switch, scoped credentials, dry-run writes with mutation diffs, loop breaker, blast-radius caps and a hash-chained audit log. No LLM calls, no phone-home,

Runtime behavior guard for coding agents (Kimi Code CLI & Claude Code): loop detection, quota gates, checkpoint/resume, supervised Wire runs

Scan AI coding agent extensions (skills, plugins, hooks, MCP servers) for unsafe patterns. Community rule pack, works with Claude Code and Grok Build.