timwis

Love that feeling when you read through a repo and think, "Wow, this looks cool," and go to star it, and see that you already have, and clearly forgot about it

Anyway, thanks for sharing. It doesn't look like it handles cli auth though (aws, npm, etc. all leave tokens sitting in your home directory). What do you use for those?

What do folks here do to avoid having plaintext credentials on disk? I try to use 1Password's plugins where I can. I find the SSH key (and got signing) experience flawless, but the cli experience (eg aws cli) pretty clunky - they often break, and they don't even have a gcp plugin last I checked.

I wish an alternative to JS for the front end would catch on and be something more than obscure... I'd love to use something like clojurescript, but I struggle to imagine doing so for anything but a personal side project :/ Maybe this is easier to adopt if you're already a clojure shop for the backend?

I've had some incredible product ideas while asleep, down to very intricate technical detail. The problem has been that when I wake up, reality kicks in, and I realise that, say, even if I built that incredible messenger app for dogs, they still wouldn't be able to communicate with us.

Really sad to see this. I had only recently learnt about this project, and was really impressed by it. I was planning to set it up this weekend (via autobase). I've also been under the impression that it's likely to be what powers the backups in RDS, Cloud SQL, etc., but I may have misunderstood.

I wondered the same! FWIW I'm currently migrating from managed postgres to self-managed on hetzner with [autobase](https://autobase.tech/). Though of course for high availability it requires more than one server.

We've started calling it dopus at work :(

I'm not the OP but I came here to voice the same concern. I would love to use something like this. I also signed up for rewind.ai and Limitless and pre-ordered the pendant. But ultimately I cancelled it out of privacy concerns.

I wonder if it could be local storage and you could provide your own Open Router endpoint? That way it could be a local model or your own deployment of GPT/Claude in Azure/Bedrock/Vertex etc where you can control retention policies etc.

Basically, I want to know that you guys don't have access to view my stuff. I get that that limits your ability to improve the product and support issues, but when I'm sending everything it really starts to matter. Just thought I'd share what held me back from immediately signing up despite really wanting to use a product like this!

This is what I do. Works great! And my caddy setup uses the DNS mode to provision TLS certs (using my domain provider's caddy plugin).

That's great news! Thanks, I'll check it out

Thanks, that's a helpful example to put it into context!

Just what I'm looking for, but I'm reluctant to trust a third party with full time screen recording of my device... Any chance of local processing (or even custom LLM endpoints) in the future?

I'm having a hard time understanding how this is different from a bastion server, where you're tunneling through an intermediary server that you've deployed in the target network.

I guess the difference is the fact that the intermediary server doesn't need a port open (as standard nat punching will work)? Or are there other big differences?

Not the OP, but I've got a "Names to remember" evergreen note in my Reference folder. Within it, I have a few headings (e.g. neighbours, or locations), and a bullet point for each person, with context that will trigger the memory. That might sound like there's a lot of structure, but it's really the act of writing it down in the first place that helps me remember.

From what I remember, the key differentiating features were:

- a heartbeat, so it was able to 'think'/work throughout the day, even if you weren't interacting with it - a clever and simple way to retain 'memory' across sessions (though maybe claude code has this now) - a 'soul' text file, which isn't necessarily innovative in itself, but the ability for the agent to edit its own configuration on the fly is pretty neat

Oh, and it's open source

Would this be any better than just pasting links to the appropriate documentation for the technology you want to use in your AGENTS.md file? I suppose it's better if it's a single giant text file so there are fewer agent iterations navigating links within the docs but then doc sites could just provide that, like https://docs.avohq.io/3.0/llm-support.html

This should work out of the box with Magic DNS (part of tailscale features). If machine A is named larrys-laptop and is running a service on :8080, then from sandras-laptop just navigate to http://larrys-laptop:8080 and it should work, provided both machines are on the same tailnet.

Hasn't cursor been doing this with it's Plan mode for a while? Or is this different?

Home Assistant have a fully local voice assistant experience that's very pluggable and customisable. I believe it uses a fast whisper model for STT and piper for TTS.

You can run it on a raspberry pi (or ideally an N100+), and for the microphone/speaker part, you can make your own or buy their off the shelf voice hardware, which works really well.

https://www.home-assistant.io/voice-pe/

Great article! I think a paragraph on your backup strategy would make it even more complete and compelling, particularly given you put your passwords and photos in there.

You can self-host Pocket ID (or another OIDC auth service) on a tiny $1/mo box and use that as your identity provider for Tailscale. Here's a video explaining how: https://www.youtube.com/watch?v=sPUkAm7yDlU

I've been looking for a solution like this for years. I briefly had an iOS shortcut on my Apple Watch working, but an OS update broke it. Now I'm on Android and I don't even know what I'd use for it. And it's exactly for these random thoughts and reminders that otherwise nag me or I forget them. David Allen (GTD) will love this too.

My only wish is that I hope it preserves the audio file, in case the transcription is wrong, so you don't lose the thought. Google Keep does this well and it's a life saver sometimes, when the transcription comes through as "Eat the cat" or something ridiculous.

Really compelling article! What do folks use instead in 2025?

Don't storage templates handle this out of the box? I haven't actually checked my instance but that was my impression from reading the docs!

What a cool post! Really enjoyed reading it.

Thanks for sharing - definitely learnt a few things reading it!

Wow, a beast. Looking forward to the next post!

One minor tip that I think can have a big impact: whenever writing down something to run on the command line (e.g. for documentation or other kind of sharing), always use the --full-version of the flags (instead of the short -f version). The extra information it conveys is worth a lot. If someone gets tired of typing it, it's easy to find the short version.

Well said! I share those two priorities, and am now moving in the inverse direction, but I plan to use GrapheneOS.

Any chance you’re selling the ePub format directly, or via the Kobo store? I switched from Kindle to Kobo a few months back, when Amazon decided to remove everyone’s ability to download the books they’ve purchased. But I’d love to read this!