OpenGuardrails AI Agent Security Platform

Project: OpenGuardrails

Situation

AI agents can read sensitive files, call tools, access credentials, and send data to external services. The system needed protection for tool-call sequences and data leaving the machine, not only prompt injection.

Task

Create a security layer that inspects agent behavior, blocks dangerous tool-call patterns, sanitizes sensitive data, and gives operators visibility into detected risks.

Action

Designed a behavioral engine that evaluates tool-call sequences and returns allow, alert, or block decisions with explanations
Added scanners for prompt injection, system override attempts, web attacks, MCP tool poisoning, malicious code execution, PII exposure, credential leakage, and confidential data
Built a local AI security gateway that sanitizes PII, credentials, and secrets before prompts reach external LLM providers, then restores values in responses
Designed a management dashboard for agents, identities, permissions, behavior graphs, and security alerts
Supported self-hosted deployment of the gateway, dashboard, and core platform, including local SQLite and an air-gapped deployment path
Packaged the platform as a CLI, gateway, and OpenClaw security plugin

Result

Created a layered runtime security model for AI agents covering behavioral controls, content scanning, data-loss prevention, and operational visibility.

Key Innovations

Tool-call sequence analysis instead of prompt-only filtering
Local secret and PII sanitization
MCP-specific threat detection
Self-hosted and air-gapped deployment options

Technologies

TypeScript, Node.js, Express, React, SQLite, Drizzle ORM, CLI tooling, OpenClaw, MCP, Anthropic, OpenAI-compatible APIs, Gemini