The main function of OpenClaw was for people to signal how advanced and cutting edge and thought-leader-y they were. All those Mac minis are sitting idle now.
I bought a Mac mini m4 before openclaw to use as a music production machine, when it turned out not to work out I tried setting up openclaw on it after hearing all the noise, but that turned out not to work out either.
I’ve found a much better use for it now. I use it as a Tailscale + ssh + tmux + Claude code machine, which gives me an always on Claude code environment with persistent sessions. I ssh from my phone using termius and from my laptop through ssh, and I can even access my projects through Tailscale with hot reloading for the most part, no deploy needed. It’s really good and my mini isn’t idle at all.
Yea I have to try it and see. When Claude released Remote Control I hoped on right away and it was crap, it kept disconnecting. Tailscale + SSH was much better.
Operations: mostly tasks and reminders, I often think of something while on the road and send a voice message (like I would to a real PA). I use Kokoro-based TTS for local text-to-speech. Anything from "remind me to discuss X with so-and-so tomorrow" to "I have a multiple PoC projects w/ large entities starting next week - think about how I can best handle that" to "brainstorm how can I maximize upfront revenue with them", etc
Sales: using Google/gemini web search API and it's best run off-peak due to rate limits 503 Service Unavailable (everyone is overbooked when it comes to AI) to see what's happening in the space, any new developments involving companies I care about - and send me a daily digest with an overview and conversation topics.
#1 is just Siri/Google Assistant with extra steps (and expense).
#2 could be a scheduled task (cron job or something higher level) that calls a plain old AI provider API. IIRC most providers can even do those natively now.
That would be valid if setting up a scheduled AI task actually took any technical knowledge, but it doesn’t. ChatGPT lets you schedule tasks natively in the UI, and I assume others do as well.
#2: Gemini also has scheduled actions. You can just ask it to give you daily digests about developments in some area, or you could even be in the middle of chatting about some current events, and tell it to notify you when there is new data, etc.
No recurring expense, just the hardware upfront cost. My next step is run the models locally as well. I used to work at FAANG (incl. compliance) and I would never use a cloud-based assistant of any kind.
Some truth to that. I hear it thrown around the office and everyone feels obligated to out agent each other (without actually proving a great use case)
For myself I don't need autonomous agents. I need a smaller version of Claude Code instead (the mcp client not the coding agent) that can run on local models that are under 24B params. I still need to try pi dev.