I installed mine the first weekend it came out. It took ~15 minutes, and then I took my kids to the library to pick out books. I sat in a chair while they were looking and had it bookmark and summarize a few links. For the hell of it, I asked it to take a screenshot of a few websites, and it sent them back 30 seconds later, to my amazement.

I haven't connected email to it, but I plan to connect my calendar so that it can build out a better daily briefing for me and possibly schedule a few things for me.

I'm running it on a Mac Mini (before it was cool), but i wouldn't buy a new machine for it or run it on a VPC unless you need it to. Run it on Tailscale, with a firewall blocking everything.

I think the platform's power lies in cron and memory. Its ability to just do things is killer too. I was in bed and got a downtime alert from some server issues I hadn't sorted out. I asked it to "ssh node..." and reboot it, and a minute later, my server was back up.

So I'm a fan, but I haven't had it do anything that generates revenue. Yet.

The screenshot text and placements throw me. You mention "Perfect text placement" but it looks off to me. Might be the overlap between the "p" and the "W" but it doesn't sell me on the overall quality.

You might consider swapping the images so they flow from left to right which is amore natural "before (other products)" to "after (our product)" with possibly an arrow in between them or a visual clue, so people understand immediately understand it.

Good luck!

Mostly @modelcontextprotocol/server-filesystem, but I have tried more out via smithery.ai

I do quite a bit of scraping and have had good luck using various AI platforms. I haven't done real estate directly, but I have pulled restaurant details to build a few database and was happy with it.

I use jina.ai a lot for various projects. I have ZERO association with them, but it does a good enough job of cleaning up a URL to pass to OpenAI or Claude with great results. I'm using the Reader API, but they have some others that might be good.

I just pass the results to an LLM and rarely look back.

I use Python 99% of the time and I have had a ton of success with OpenAI + Structured data. I'm a few weeks into using PydanticAI for nice JSON/structured data out and I love using it. (also no association) ai.pydantic.dev/results/

Taxes are unavoidable if you are collecting them in the US.

A US LLC is only going to make it easier for you to take US transactions and payments, but that's about it. You'll still need a US Bank + address to make taking US checks easier, you'll still have to file US taxes even if it's mostly passing through to you personally, and you'll still need to pay for the filing and possibly an accountant to handle it for you. The business (LLC) will still owe taxes on US income from businesses, even if your personal income doesn't have to pay US taxes out of what you pay yourself. I'm not sure how you get around that.

This is great and a nice way to end the year. Monthly or quarterly would be fine too, but annual is good enough imo.

Not sure if you have a kid or not, but another thing new parents struggle with are the once-a-month photos that show the babies age in months in a cute scene. That might have some potential if your newborn photo is too narrow of a market.

It's more of an orchestration and weaving them together than a deployment and hosting issue.

So far, I have tested by hand, but I have a few scripts where I turned the temperature down, and I seem to get the same results 100% of the time. This is for things like parsing salary details from a job posting, etc.

I don't struggle with writing them or testing them, but I have yet to find a good way to share and run them. I have several I can run from my terminal for scheduling meetings, but I don't really want a dozen agents running their own chat servers.

I am looking into PydanticAI because I use Pydantic for almost every one of my apps these days. I have also been using Anthropic's MCP framework which is amazing, but it only runs locally so far. I suspect one or both of those are going to make it easier for me to run Agents across dozens of apps, but I'm not there yet.

I also haven't seen a great way to chain Agents together as some of the DAG frameworks (like Airflow) do with tasks. I could be overthinking it, but this feels like it should be tackled.