Skip to main content
Back to all repositories
ER

sanctuary-framework

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.

8stars0forks0watchers/subscribers25issues
agent-infrastructureai-agent-securityai-agentsclaude-codedecentralized-identityegress-controlendpoint-securitymcpmcp-serveropen-standardprivacy
Language
TypeScript
License
Apache License 2.0
Size
60.1 MB
Created
Mar 22, 2026
Last Updated
Sep 4, 2026
Last Pushed
Sep 4, 2026

Available Plugins

Loading plugins...

Evaluate before installing

  1. Review the source repository, recent maintenance, and license on GitHub.
  2. Read the marketplace manifest and plugin source files before running commands.
  3. Start with the smallest required permission set and validate behavior in a safe environment.