sanvexdev/sanvex ? reverse-engineered prompt
Reverse engineered prompt
Build me a Laravel package that gives me one simple way to connect AI agents and apps to services like GitHub, Gmail, Linear, Notion, and Slack through a single manager. I want to be able to register a driver, load it for a specific user or workspace, and then call things like list repos, read messages, or create issues with a clean resolveDriver() style flow.
Please include the core package, a small CLI for setup and scaffolding, and support for optional agent access through MCP so tools can be exposed to an AI client. Make it easy to encrypt credentials, support multi tenant use, and let me add custom drivers later. If you need to check current Laravel or package docs while building it, go ahead and look them up online.
Are you gonna build this?
make sure you review the code using coderabbit