# PromptGuard

> Production-grade AI security firewall. Protect LLM applications from prompt injection, data leaks, jailbreaks, and PII exposure.

PromptGuard sits between your application and LLM providers, scanning every request and response through a six-layer detection pipeline (normalization, regex, ML ensemble, content safety, multi-turn drift, policy evaluation) with <200ms P95 latency.

## Quick Start

- Sign up: https://app.promptguard.co
- Documentation: https://docs.promptguard.co
- API Reference: https://docs.promptguard.co/api-reference/introduction
- Python SDK: pip install promptguard-sdk
- Node.js SDK: npm install promptguard
- CLI: curl -fsSL https://raw.githubusercontent.com/acebot712/promptguard-cli/main/install.sh | sh

## Core Concepts

- Auto-instrumentation: One line of code secures all LLM calls
- Guard API: POST /api/v1/guard for standalone message scanning
- HTTP Proxy: Swap your LLM base URL to https://api.promptguard.co/api/v1
- Security Policies: Presets (default, support_bot, code_assistant, rag_system) or custom YAML
- PII Redaction: 39+ entity types across 10+ countries
- Red Team: Autonomous adversarial testing of your security posture

## Documentation

- [Quick Start](https://docs.promptguard.co/quickstart)
- [Authentication](https://docs.promptguard.co/authentication)
- [Python SDK](https://docs.promptguard.co/sdks/python)
- [Node.js SDK](https://docs.promptguard.co/sdks/node)
- [CLI](https://docs.promptguard.co/tools/cli)
- [MCP Server](https://docs.promptguard.co/tools/mcp)
- [Security Overview](https://docs.promptguard.co/security/overview)
- [Threat Detection](https://docs.promptguard.co/security/threat-detection)
- [Custom Rules](https://docs.promptguard.co/security/custom-rules)
- [Policy as Code](https://docs.promptguard.co/security/policy-as-code)
- [Proxy Configuration](https://docs.promptguard.co/advanced/proxy-config)
- [Error Handling](https://docs.promptguard.co/advanced/error-handling)
- [Rate Limits](https://docs.promptguard.co/advanced/rate-limits)
- [Webhooks](https://docs.promptguard.co/monitoring/webhooks)
- [Pricing](https://docs.promptguard.co/pricing)
- [API Reference](https://docs.promptguard.co/api-reference/introduction)

## API Endpoints

- POST /api/v1/guard - Scan messages for threats (input/output)
- POST /api/v1/security/scan - Standalone content scanning
- POST /api/v1/security/redact - PII redaction
- POST /api/v1/chat/completions - Proxied OpenAI-compatible completions
- POST /api/v1/messages - Proxied Anthropic-compatible messages
- GET /api/v1/models - List available models
- POST /api/v1/redteam/* - Red team testing endpoints

## Links

- Website: https://promptguard.co
- Dashboard: https://app.promptguard.co
- Status: https://status.promptguard.co
- GitHub: https://github.com/acebot712
- Support: support@promptguard.co