yoheinakajima/babyagi ? reverse-engineered prompt

Reverse engineered prompt

Build me a small experimental Python project that feels like a self building agent playground, not a production app. I want to be able to register normal Python functions, save and manage them through a simple system, and let functions depend on other functions, outside imports, and secret API keys. It should be easy to run a function, update it, load a pack of functions from a file, and have the app automatically keep track of what depends on what.

Please include a lightweight web dashboard at something like /dashboard where I can browse functions, add or update them, manage keys, see dependency relationships, set simple triggers, and inspect logs of every run including inputs, outputs, timing, and errors. The logging should make it easy to understand what happened when one function calls another.

Include a tiny hello world style example so I can test it fast, and keep the whole thing usable locally on port 8080. If anything is unclear, check the current project docs online and make sensible choices.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab