akitaonrails/FrankClaw ? reverse-engineered prompt

Reverse engineered prompt

Build me a secure personal AI assistant gateway in Rust that connects a few messaging channels like web chat, Telegram, Discord, Slack, Signal, WhatsApp, and email to different AI providers through a local control plane.

I want one app that can route requests to the right model, fall back if a provider fails, keep track of costs and daily limits, and cache replies so it does not repeat work. It should also support tools like browser automation, shell commands with safety checks, scheduled jobs, and a simple plugin system. Please include a web console for chatting, managing agents, viewing logs, checking usage, and approving risky actions, plus a terminal chat mode for power users.

Make it secure by default, with encrypted sessions, strong input validation, leak detection for secrets, and sane defaults for tool access. If needed, look up current docs online while implementing it, and make it easy to run locally with Docker.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab