beelzebub-labs/beelzebub ? reverse-engineered prompt

Reverse engineered prompt

Build me a Go based deception runtime that I can run locally, in Docker, or in Kubernetes, with a simple CLI to start the services and validate the config. I want it to act like realistic decoy systems over SSH, HTTP, TCP, TELNET, and MCP, and to use an LLM when needed so the responses feel believable and adaptive instead of canned. Let me define services with easy YAML config, and make it possible to plug in custom response handlers without changing the core app.

It should also keep track of activity with Prometheus metrics, support event streaming through RabbitMQ, and shut down cleanly. Include a basic install script, Docker support, and a Helm chart. If you need to check current docs for any integration details, go look them up online first.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab