clawtower

Official

Tamper-proof OS watchdog for AI agents.

AuthorClawTower
Version1.0.0
Installs0

System Documentation

What problem does it solve?

ClawTower is a tamper-proof OS-level security watchdog designed to protect AI agents by monitoring the host for threats, tampering, and policy violations, ensuring the agent cannot disable or modify it.

Core Features & Use Cases

  • Tamper-proof, OS-level monitoring using auditd, inotify, network policy, and file integrity checks to detect and alert on threats or policy violations.
  • Immutable binaries and swallowed key security model to prevent tampering and ensure accountability; supports admin-side workflows via clawsudo, restore-keys, and compliance tooling.
  • Integrations for dashboards and alerts (TUI, web dashboard, Slack) and APIs for status, health, and evidence, along with compliance reporting and auditing commands.

Quick Start

Install ClawTower non-interactively using the on-shot installer to bootstrap on a Linux host.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: clawtower
Download link: https://github.com/ClawTower/ClawTower/archive/main.zip#clawtower

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.