Discover and explore top open-source AI tools and projects—updated daily.
denolandSecurity firewall for AI agents
New!
Top 85.6% on SourcePulse
Summary
Claw Patrol is a security firewall designed to protect production environments from agent actions. It intercepts and inspects agent traffic, enforcing custom rules written in HCL to prevent potentially destructive or unauthorized operations before they reach their targets. This provides a crucial safety layer for AI agents and automated systems interacting with sensitive infrastructure.
How It Works
The system operates by parsing network traffic at the wire level for various protocols, including SQL, Kubernetes, and HTTP. It extracts protocol-specific facts (e.g., SQL verbs, Kubernetes resource types, HTTP methods/paths) which are then evaluated against user-defined rules. These rules, written in HashiCorp Configuration Language (HCL), leverage Common Expression Language (CEL) for conditions, allowing for precise and expressive security policies. This approach offers granular control, enabling developers to define specific actions that are permitted or denied, thereby mitigating risks associated with autonomous agent behavior.
Quick Start & Requirements
curl -fsSL https://clawpatrol.dev/install.sh | sh.make.Highlighted Details
gateway (a standalone proxy), join (host-wide WireGuard tunnel), and run (per-process tunnel for Linux/macOS).Maintenance & Community
No specific details on contributors, sponsorships, or community channels were provided in the README.
Licensing & Compatibility
Limitations & Caveats
No specific limitations, alpha status, or known issues were detailed in the provided README excerpt.
1 day ago
Inactive