| title | Product Overview |
|---|---|
| description | A complete look at the Panguard AI product suite, architecture, technology stack, and subscription tiers. |
| icon | shield-check |
Panguard AI is an open-source cybersecurity platform designed for developers and small businesses who do not have a security team. It combines rule-based detection, local AI, and cloud AI into a single CLI tool that protects endpoints automatically.
The user experience mirrors tools like Claude Code:
- Website -- Browse plans, sign up, manage subscriptions at panguard.ai
- CLI --
panguard loginopens the browser for authentication; the token is stored locally - Usage -- Features are gated by subscription tier; daily operation is zero-effort
Panguard AI includes 8 products. Each works independently, but together they form a complete Security Operations Center in one command.
**60-Second Security Audit** -- One-time scan producing a risk score (0-100, grades A-F) and PDF report. Covers ports, services, firewall, SSL/TLS, password policy, and more. **AI Real-Time Monitoring** -- Always-on protection with a 4-agent AI pipeline (Detect, Analyze, Respond, Report). 7-day learning period, 3,155 Sigma rules, 5,895 YARA rules, and auto-response capabilities. **AI Security Notifications** -- Translates technical alerts into plain language. Delivers via Telegram, Slack, Email, Webhook, or LINE with three tone modes: boss, developer, and it_admin. **Smart Honeypots** -- 8 decoy services (SSH, HTTP, FTP, SMB, MySQL, RDP, Telnet, Redis) that lure attackers, collect intelligence, and profile attacker skill levels. **Compliance Reports** -- Auto-generate audit-ready reports for Taiwan TCSA (10 controls), ISO 27001 (30 controls), and SOC 2 (10 controls) in 60 seconds. **Model Context Protocol** -- Integrate Panguard security data with AI assistants and LLM-powered workflows through the MCP server. **Multi-Endpoint Management** -- Centralized dashboard for managing multiple Panguard agents across a fleet with policy enforcement and lifecycle management. **Collective Threat Intelligence** -- Anonymized threat signature sharing across the Panguard network. RESTful API with SQLite backend, automatic Sigma rule generation, and IP/domain reputation scoring.Panguard uses a layered AI funnel that balances speed, cost, and accuracy. Each layer handles progressively fewer -- but more complex -- events.
| Layer | Technology | Handles | Latency | Cost |
|---|---|---|---|---|
| Layer 1 | Sigma / YARA rules engine | 90% of events | < 50ms | $0 |
| Layer 2 | Local AI (Ollama) | 7% of events | ~2s | $0 |
| Layer 3 | Cloud AI (Claude / OpenAI) | 3% of events | ~5s | ~$0.008/call |
For a deep dive into the AI architecture, see Three-Layer AI.
| Category | Technology |
|---|---|
| Language | TypeScript 5.7 (strict mode) |
| Runtime | Node.js 20+ |
| Monorepo | pnpm 10 workspaces |
| Testing | Vitest 3 (3,017 tests / 142 files) |
| Detection Rules | Sigma (3,155) + YARA (5,895) + Suricata + Falco |
| AI Providers | Ollama (local) + Claude / OpenAI (cloud) |
| Authentication | Google OAuth (PKCE) + scrypt hashing |
| Internationalization | English + Traditional Chinese |
| Encryption | AES-256-GCM |
| Feature | Community | Solo | Pro | Business |
|---|---|---|---|---|
| Price | Free | $9/mo | $29/mo | $79/mo |
| Machines | 1 | 3 | 10 | 25 |
| Scan (unlimited) | Yes | Yes | Yes | Yes |
| Guard (Layer 1 rules) | Yes | Yes | Yes | Yes |
| Guard (Full 3-layer AI) | -- | Yes | Yes | Yes |
| Chat notifications | -- | Yes | Yes | Yes |
| Local AI (Ollama) | -- | Yes | Yes | Yes |
| Cloud AI analysis | -- | -- | Yes | Yes |
| Trap (8 honeypots) | -- | -- | Yes | Yes |
| Compliance reports | -- | -- | Yes | Yes |
| SIEM integration | -- | -- | -- | Yes |
| SSO and RBAC | -- | -- | -- | Yes |
| Dedicated support | -- | -- | -- | Yes |
Compliance reports are available as one-time purchases on Pro and Business plans:
| Report | Price | Controls |
|---|---|---|
| Taiwan TCSA | $299 | 10 |
| ISO 27001 | $499 | 30 |
| SOC 2 | $699 | 10 |
| Bundle (all 3) | $999 | 50 |
Annual billing receives a 20% discount on all subscription plans. Manage your subscription at panguard.ai/pricing.
Panguard AI is released under the MIT License. Full source code. Zero black boxes. Every line is auditable.
Browse the source code, report issues, or contribute to the project.