This reminds me so much of my own experience with AI fueled dev mania. Rapidly build semi-functional wonders, then pivot to something shiny and new to avoid the QA trudge of polishing that wonderous turd.
It uses your existing subscriptions and supports all the major CLI and API providers. There's no cloud features of Omnispect itself, it runs locally except for calls to the LLM providers.
Claude Opus 4.5 is used as a routing agent, which selects the most appropriate LLM provider and model tier to delegate a task to. For example, the routing agent might delegate a single large task to GPT-5, which in turn delegates multiple small tasks to Haiku agents in parallel, then Gemini reviews all the work.
Omnispect lets you view the delegation tree of prompts and responses that spawn from your initial prompt.
Nice, great minds think alike! Not having vendor lock in and being flexible to use multiple providers and models gives us the most flexibility. The investments put into the CLI tools and what they can do are also amazing, I love using them.
I have looked before and never found one. I just spent ten minutes on Google now and got nothing except for identical replacement bricks. Some by third parties but looking exactly the same.
If you know of something better please share a link.
Externally supplied hot water through a plastic tube makes this a non-starter for me. You use almost no plastic (wonderful!), but the little there is has a lot of surface area touching hot water.
Have you thought about making a water heater accessory? I'd be open to collaborating - contact[at]otekengineer.com
That grinder is a thing of beauty. I was going to impulsively splurge until I saw the price (not complaining, you're doing the right thing by launching at a high price point).
I'm on my second agent orchestration framework, Omnispect - https://omnispect.dev/
Example created by Omnispect:
Oneshot - https://omnispect.dev/battleclone00.html
Polished - https://omnispect.dev/battleclone04.html
reply