# Panguard AI - Security for AI Agents

## Docs

- [API Overview](https://docs.panguard.ai/api-reference/overview.md): Panguard AI exposes the Threat Cloud REST API for threat intelligence.
- [Campaigns](https://docs.panguard.ai/api-reference/threat-cloud/campaigns.md): Track coordinated attack campaigns identified through IoC correlation.
- [Feed Endpoints](https://docs.panguard.ai/api-reference/threat-cloud/feeds.md): Consume threat intelligence feeds in blocklist and structured JSON formats.
- [IoC Endpoints](https://docs.panguard.ai/api-reference/threat-cloud/ioc.md): Upload threat intelligence and query Indicators of Compromise (IoCs) from the Threat Cloud.
- [Statistics & Queries](https://docs.panguard.ai/api-reference/threat-cloud/stats.md): Advanced analytics endpoints for time series, geographic distribution, MITRE heatmaps, sightings, and audit logs.
- [ATR (Agent Threat Rules)](https://docs.panguard.ai/atr.md): Open standard for detecting threats to AI agents. 419 rules. OWASP Agentic Top 10: 10/10 covered. Community-maintained.
- [panguard config](https://docs.panguard.ai/cli/config.md): View and edit the Panguard CLI configuration.
- [panguard doctor](https://docs.panguard.ai/cli/doctor.md): Diagnose and troubleshoot common Panguard system issues.
- [panguard guard](https://docs.panguard.ai/cli/guard.md): Manage the real-time endpoint protection agent.
- [panguard init](https://docs.panguard.ai/cli/init.md): Initialize Panguard configuration for the current machine.
- [CLI Overview](https://docs.panguard.ai/cli/overview.md): Unified command-line interface for all Panguard AI security operations.
- [panguard report](https://docs.panguard.ai/cli/report.md): Generate compliance and audit reports aligned with major security frameworks.
- [panguard scan](https://docs.panguard.ai/cli/scan.md): Run security vulnerability scans on the local machine.
- [panguard status](https://docs.panguard.ai/cli/status.md): Display the overall health and status of all Panguard services.
- [panguard threat](https://docs.panguard.ai/cli/threat.md): Start a local Threat Cloud intelligence server for aggregating and querying threat data.
- [panguard upgrade](https://docs.panguard.ai/cli/upgrade.md): Update the Panguard CLI to the latest version.
- [System Architecture](https://docs.panguard.ai/concepts/architecture.md): Technical architecture overview of the Panguard AI platform: monorepo structure, deployment layers, and component interactions.
- [Learning Mode](https://docs.panguard.ai/concepts/learning-mode.md): How Panguard Guard spends 7 days learning your system's normal behavior before activating protection.
- [Security Score](https://docs.panguard.ai/concepts/security-score.md): How Panguard calculates your system's risk score from 0-100 with letter grades A through F.
- [Threat Intelligence](https://docs.panguard.ai/concepts/threat-intelligence.md): Real-time threat intelligence feeds and the Threat Cloud collective intelligence network.
- [Three-Layer AI Funnel](https://docs.panguard.ai/concepts/three-layer-ai.md): How Panguard processes 90% of security events in under 1ms using a cascading Rules, Local AI, and Cloud AI architecture.
- [Environment Variables](https://docs.panguard.ai/configuration/environment-variables.md): Complete reference for all environment variables across Panguard services.
- [Guard Configuration](https://docs.panguard.ai/configuration/guard-config.md): Complete reference for the Panguard Guard configuration file.
- [Getting Started](https://docs.panguard.ai/getting-started.md): Install Panguard AI and start protecting your AI agents in under 5 minutes.
- [Install on OpenClaw & Compatible Platforms](https://docs.panguard.ai/guides/claw-setup.md): One-command setup guide for OpenClaw, QClaw, WorkBuddy, NemoClaw, and ArkClaw. No account required.
- [Docker Deployment](https://docs.panguard.ai/guides/docker-deployment.md): Run Panguard AI with Docker and Docker Compose for containerized security monitoring.
- [Your First Scan](https://docs.panguard.ai/guides/first-scan.md): Step-by-step guide to running your first Panguard security scan, understanding the results, and taking action on findings.
- [Integrate with AI Assistants via MCP](https://docs.panguard.ai/guides/mcp-integration.md): Connect Panguard to Claude Desktop, Cursor, or Windsurf using the Model Context Protocol for AI-assisted security operations.
- [Multi-Endpoint Setup](https://docs.panguard.ai/guides/multi-endpoint.md): Deploy the Panguard Manager for fleet-wide security orchestration across multiple machines.
- [Configure Notifications](https://docs.panguard.ai/guides/notifications-setup.md): Set up alert channels so Panguard can notify you of threats via Telegram, Slack, Email, LINE, or Webhook.
- [Real-Time Protection](https://docs.panguard.ai/guides/real-time-protection.md): Set up Panguard Guard for continuous monitoring, learn how the 7-day learning period works, and configure automated threat response.
- [System Service](https://docs.panguard.ai/guides/system-service.md): Install Panguard Guard as a systemd, launchd, or Windows service for automatic startup and continuous protection.
- [Deploy Threat Cloud](https://docs.panguard.ai/guides/threat-cloud-deployment.md): Run a self-hosted Threat Cloud server for centralized threat intelligence with full privacy control.
- [Installation](https://docs.panguard.ai/installation.md): One command to install. Dashboard opens automatically.
- [Panguard AI](https://docs.panguard.ai/introduction.md): The first open standard for AI agent security. 419 ATR detection rules. OWASP Agentic Top 10: 10/10 covered. 16 platforms. Community is free and open source.
- [Product Overview](https://docs.panguard.ai/overview.md): Panguard AI -- the open standard for AI agent security. Three pillars: ATR (the standard), Threat Cloud (collective immunity), Guard (the engine).
- [Agent Pipeline (DARE)](https://docs.panguard.ai/products/guard/agent-pipeline.md): Deep dive into the 4-agent Detect-Analyze-Respond-Report pipeline that processes every security event.
- [Auto-Response](https://docs.panguard.ai/products/guard/auto-response.md): Automated threat response modules, safety rules, escalation ladder, and rollback support.
- [Event Correlation](https://docs.panguard.ai/products/guard/event-correlation.md): Real-time pattern-based multi-step attack detection using a sliding time window and 7 correlation patterns.
- [Monitor Types](https://docs.panguard.ai/products/guard/monitors.md): Reference for all 10 monitor types: 4 built-in and 6 advanced monitors with their capabilities and dependencies.
- [Panguard Guard](https://docs.panguard.ai/products/guard/overview.md): 24/7 AI-driven real-time threat monitoring with the DARE pipeline, 10 monitor types, event correlation, and automated response.
- [Panguard MCP Server](https://docs.panguard.ai/products/mcp/overview.md): Model Context Protocol server exposing 12 Panguard security tools to AI assistants like Claude Desktop, Cursor, and Windsurf.
- [MCP Tools Reference](https://docs.panguard.ai/products/mcp/tools-reference.md): Complete parameter reference and usage examples for all 12 Panguard MCP tools.
- [Product Suite Overview](https://docs.panguard.ai/products/overview.md): Panguard AI ships integrated products that cover the full security lifecycle -- from scanning and detection to response, compliance, and collective intelligence.
- [Panguard Scan](https://docs.panguard.ai/products/scan/overview.md): 60-second security health check with 10 scanners, risk scoring, and PDF report generation.
- [PDF Reports](https://docs.panguard.ai/products/scan/pdf-reports.md): Structure, sections, and customization options for Panguard Scan PDF reports.
- [Risk Scoring](https://docs.panguard.ai/products/scan/risk-scoring.md): How Panguard Scan calculates the 0-100 risk score and A-F letter grade.
- [Scanner Types](https://docs.panguard.ai/products/scan/scanners.md): Detailed reference for all 10 scanner types included in Panguard Scan.
- [Connecting to Threat Cloud](https://docs.panguard.ai/products/threat-cloud/deployment.md): How Panguard agents connect to Threat Cloud for collective threat intelligence.
- [Threat Cloud](https://docs.panguard.ai/products/threat-cloud/overview.md): Community-driven ATR rule consensus platform. Scanners propose threat patterns, the community confirms them, and confirmed rules are distributed back to all scanners.
- [Privacy](https://docs.panguard.ai/products/threat-cloud/privacy.md): How Panguard Threat Cloud anonymizes data, enforces zero telemetry, and supports full opt-out for air-gapped environments.
- [Quick Start](https://docs.panguard.ai/quickstart.md): One command. Dashboard opens. You're protected.
- [Skill Auditor](https://docs.panguard.ai/skill-auditor.md): Scan MCP skills for security threats before installation. Powered by the unified scan-core engine shared between CLI, Website, and Guard.
- [Threat Cloud](https://docs.panguard.ai/threat-cloud.md): Collective threat intelligence for AI agent security. Community-driven rules, anonymous sharing, real-time feeds.
- [Common Issues](https://docs.panguard.ai/troubleshooting/common-issues.md): System requirements, supported platforms, updating, and uninstalling Panguard AI.
- [Guard Issues](https://docs.panguard.ai/troubleshooting/guard-issues.md): Troubleshoot Panguard Guard startup, performance, and detection problems.
- [Notification Issues](https://docs.panguard.ai/troubleshooting/notification-issues.md): Troubleshoot Telegram, Slack, Email, and Webhook notification delivery problems.
- [ATR (Agent Threat Rules)](https://docs.panguard.ai/zh-Hant/atr.md): AI agent 威脅偵測的開放標準。419 條規則。OWASP Agentic Top 10: 10/10 覆蓋。社群維護。
- [系統架構](https://docs.panguard.ai/zh-Hant/concepts/architecture.md): Panguard AI 的技術架構：monorepo 結構、部署層級、元件互動。
- [學習模式](https://docs.panguard.ai/zh-Hant/concepts/learning-mode.md): Guard 花 7 天學你系統的正常行為，才開始防護。不是偷懶，是為了不亂叫。
- [安全分數](https://docs.panguard.ai/zh-Hant/concepts/security-score.md): Panguard 怎麼算出 0-100 的系統風險分數和 A 到 F 等級。
- [威脅情報](https://docs.panguard.ai/zh-Hant/concepts/threat-intelligence.md): 即時威脅情報 feed 和 Threat Cloud 集體情報網路。
- [三層式 AI 漏斗](https://docs.panguard.ai/zh-Hant/concepts/three-layer-ai.md): Panguard 怎麼用級聯式架構在 1ms 內處理 90% 的安全事件 -- 規則、本地 AI、雲端 AI 三層搞定。
- [環境變數](https://docs.panguard.ai/zh-Hant/configuration/environment-variables.md): Panguard 各服務環境變數完整參考。
- [Guard 設定](https://docs.panguard.ai/zh-Hant/configuration/guard-config.md): Panguard Guard config 檔完整參考。
- [開始使用](https://docs.panguard.ai/zh-Hant/getting-started.md): 安裝 Panguard AI，5 分鐘內開始保護你的 AI agent。
- [安裝到 OpenClaw 及相容平台](https://docs.panguard.ai/zh-Hant/guides/claw-setup.md): OpenClaw、QClaw、WorkBuddy、NemoClaw、ArkClaw 一鍵安裝指南。不需帳號。
- [Docker 部署](https://docs.panguard.ai/zh-Hant/guides/docker-deployment.md): 用 Docker 和 Docker Compose 跑 Panguard AI，容器化安全監控。
- [第一次掃描](https://docs.panguard.ai/zh-Hant/guides/first-scan.md): 手把手帶你跑第一次 Panguard 安全掃描，看懂結果，知道該修什麼。
- [透過 MCP 整合 AI 助手](https://docs.panguard.ai/zh-Hant/guides/mcp-integration.md): 用 MCP 把 Panguard 接上 Claude Desktop、Cursor 或 Windsurf，用自然語言做安全操作。
- [多端點部署](https://docs.panguard.ai/zh-Hant/guides/multi-endpoint.md): 部署 Panguard Manager，跨多台機器進行機群安全管理。
- [設定通知](https://docs.panguard.ai/zh-Hant/guides/notifications-setup.md): 設定警報頻道，讓 Panguard 透過 Telegram、Slack、Email、LINE 或 Webhook 通知你威脅事件。
- [即時防護](https://docs.panguard.ai/zh-Hant/guides/real-time-protection.md): 設定 Guard 持續監控系統、了解 7 天學習期怎麼運作、設定自動威脅回應。
- [系統服務](https://docs.panguard.ai/zh-Hant/guides/system-service.md): 把 Guard 裝成 systemd、launchd 或 Windows 服務，開機自動跑、持續防護。
- [部署 Threat Cloud](https://docs.panguard.ai/zh-Hant/guides/threat-cloud-deployment.md): 自架 Threat Cloud 伺服器，集中管理威脅情報，資料完全掌握在自己手上。
- [安裝](https://docs.panguard.ai/zh-Hant/installation.md): 一行指令安裝。Dashboard 自動開啟。
- [Panguard AI](https://docs.panguard.ai/zh-Hant/introduction.md): AI Agent 安全的第一個開放標準。419 條 ATR 偵測規則。OWASP Agentic Top 10: 10/10 覆蓋。16 個平台。Community 永久免費開源。
- [產品總覽](https://docs.panguard.ai/zh-Hant/overview.md): Panguard AI -- AI Agent 安全的開放標準。三大支柱：ATR（標準）、Threat Cloud（集體免疫）、Guard（引擎）。
- [快速入門](https://docs.panguard.ai/zh-Hant/quickstart.md): 一行指令。Dashboard 自動開。你已經受保護了。
- [Skill Auditor](https://docs.panguard.ai/zh-Hant/skill-auditor.md): 安裝 MCP Skill 前先掃描安全威脅。用 scan-core 統一引擎，CLI、網站、Guard 共用同一套偵測邏輯。
- [Threat Cloud](https://docs.panguard.ai/zh-Hant/threat-cloud.md): AI agent 安全的集體威脅情報。社群驅動的規則、匿名分享、即時更新。
- [常見問題](https://docs.panguard.ai/zh-Hant/troubleshooting/common-issues.md): 系統需求、支援平台、更新跟解除安裝 Panguard AI。
- [Guard 問題](https://docs.panguard.ai/zh-Hant/troubleshooting/guard-issues.md): 排解 Panguard Guard 啟動、效能跟偵測的問題。
- [通知問題](https://docs.panguard.ai/zh-Hant/troubleshooting/notification-issues.md): 排解 Telegram、Slack、Email、Webhook 通知送不到的問題。

## OpenAPI Specs

- [openapi](https://docs.panguard.ai/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/panguard-ai/panguard-ai)