eriknewton

Sanctuary Framework

Name: Sanctuary Framework
Author: eriknewton

Security community

SOURCE https://github.com/eriknewton/sanctuary-framework

Description

Open-source security for AI agents: kernel-enforced egress control on macOS and Linux, keys only the operator holds, tamper-evident audit. One command protects Claude Code, Cursor, or any MCP harness. No vendor in the path.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Sanctuary

[![CI](https://github.com/eriknewton/sanctuary-framework/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/eriknewton/sanctuary-framework/actions/workflows/ci.yml) [![npm version](https://img.shields.io/npm/v/@sanctuary-framework/mcp-server.svg)](https://www.npmjs.com/package/@sanctuary-framework/mcp-server) [![License](https://img.shields.io/npm/l/@sanctuary-framework/mcp-server.svg)](LICENSE)

**Your agent will know you better than you know yourself. Make sure that stays between you.**

Sanctuary is the open source standard for secure, private AI: operating-system enforcement is live on macOS today; Linux and Windows are not live enforcement yet. Your data stays under your own keys, with current portability bounds called out in the Assurance Matrix. Any agent, local or cloud, solo or fleet. One command to get started. One dashboard to secure them all.

Sanctuary wraps any AI agent, on your machine or in your cloud, so actions flow through policy gates, platform-proven walls, operator-held keys, and an audit trail you can actually read. One dashboard manages the security and privacy of every agent you run, whether that is one agent on your laptop or a whole fleet across your machines. Your data, and the reputation your agents build, stay on hardware you control, with exit-bundle gaps still open for dashboard export, skipped import counters, and rotated-key import.

Already running Claude Code, Cursor, Hermes, OpenClaw, Cline, or Mastra?

npx @sanctuary-framework/mcp-server protect --claude-code

That one command puts the keys, audit trail, policy gates, and dashboard around the agent you already use. The operating-system wall is a separate privileged arming step on macOS through the signed app and extension path. See the [Castle Wall macOS install and arm guide](docs/castle-wall-macos-install.md) for the customer path from download to verified armed state. You keep your harness; Sanctuary adds the protection underneath.