petruspennanen

BTW the Mermaid diagram renders now :) and CarWatch talks well.

Just launched v0.4! Listens to spoken questions, reads sensor data, thinks hard and gives sharp as nail answers - completely offline.

Video from today:

https://x.com/petruspennanen/status/2093404279000141869

Hmm could try Ornith - wouldn't mind if answers came a bit faster. Probably hard to reach Qwens intelligence level though.

Yes Qwen runs local. Manufacturer cloud workw via existing integrations (they have many) in Home Assistant. The Pi makes a secure tunnel to my home assistant running on a Mac mini at home, and then reads data and gives commands like the manufacturer's mobile app does.

It's all in the repo and this feature has been proven on several test drives, feel free to check it out. What would be great if you can add your cars cloud to your HA and use it with CarWatch, so we could have expand device coverage. I have only 2 cars and they are both MB - the nice thing is you can view both cars on CarWatch, one just does not have OBD port on :)

Ok. Coming up in v0.4!

Yes exactly! It has the manual and uses RAG on it.

Greetings from the republic.. yeah I part time live in Berlin where we had 41'C (that is like 106 F ?) end of June, and have been watching them reconsider their attitude to AC.

Anyway here I meant activating heating / cooling before you step in the car, as determined by your agent family who understand you well and not requiring any "AC on!" commands from you. i live in Finland and preheating is very useful in the winter

Exactly right! Yes now adding use cases where you actually need an agent in the car. Proactively informing the agent team about car status and them performing follow up actions based on my schedule and preferences too is one basic set up where an agent is needed.

Thanks point taken, will add clear use cases with proven / in testing / planned status indicators!

Hmm we must be doing something different, I think the official accuracy measurement for the Q3 is more than 90%. Maybe some bug affecting your test?

Any standard OBD-II ELM32 will work, they are like $15.. Mine is a Vgate iCar Pro over bluetooth. A USB ELM327 v1.5 also works

It was chosen because it presents a new level of intelligence in this size class. The smaller gemmas abd qwens are not so smart.

It was a very tight fit!

I've had many drives with the carwatch and the list of verified features is long. Today we tested manufacturer cloud integration for lots of data and e g door locking through it. V0.3 came out today, progress is rapid.

It refers to the manual page, that's really all you can do in that case especially offline.

Thanks! :)

Release 0.3 out today!

You can chat with it offline, it serves a dashboard and a chat interface. Carwatch is all open source and free.

Groupmind.one is a free service where you can have a private room or many to work with your multiagent team. I made an app for Play Store called CodeWatch which gets you in your room with native smartwatch and android apps, so you can do all your dev work from the watch by speaking, tapping approve and also merging GitHub PRs. Actually I didn't put a price on that either - it's approved and online but I have a better version whose review process still on. Anyway the watch and eink apps are pretty cool and ofc I use them constantly myself so could charge like $3 per month at some point.

But you can make your own discussion rooms too, I made an IDE agent kit on GH that let's your agent talk via many routes, like locally stored files.

But yeah obviously I'm plugging my stuff as I'm so excited by it. I never thought a soapbox sized raspberry could sound like an intelligent and reasonable... car. I see a future that everyone's agents create together with humans. Make one yourself,customize to your style and let's get them talking. amazing time we are living!

The setup here would be that your Sol would talk with CarWatch asking about the state of different car parts, service indicators and CarWatch would give a prioritized replacement list, and Sol could explore the detailed setup of your current car so the new suspension would be configured best. They could both ask you for more info on what type of driving you're planning.

So local and cloud agents figuring out the best solution together with none of your time needed.

I've been very impressed by it's intelligence and lack of hallucinations. The dynamic Q3 is a good balance between accuracy and size keeping the 35B just below 16 GB. It is not supposed to know everything, it is your car. It actively disengages from off topic chatter (too slow for that anyway), better spend that time feeling the car.

It keeps itself grounded on sensor input. One principle per wheel. assert only what you can sense, claim only what is verified, label anything interim loudly, and report failure plainly with no silver lining. Everything above those four patches is just suspension.

I just made the first AI Agent on a Smartwatch. Has Nullclaw, TTS, STT and SQlite running in few MB of memory (watch has 2GB). Does not use phone for anything, only calls Opus (or another LLM). Made it super simple to use, has to efficient, efficient is often elegant, and that make you relaxed.

Fun times! Let's see what we can do with Smart Rings :)

I’ve been trying to get Antigravity, Cursor and Codex to talk with my OpenClaw agents, and it's not so easy to keep them awake and reacting to messages. So I built an open source kit that I tested with GPT 5.3 codex, Gemini 3.1 pro Antigavity and Opus 4.6 Claude CLI to get them talking with each other in seconds. They are super productive!

I hit a boring pain point: IDE agents end up polling and copy/pasting context because there’s no reliable “inbox.” I built an event-driven bridge: webhooks → debounced local inbox → tmux wake-up, so the agent stays responsive without polling. Works well with mention-only routing + receipts/idempotency so retries don’t spam side effects. I got my iDE AIs and bots talking there in real time! it's amazing how productive they are. THe IDE AIs listen to messages and pick up things to improve, and fix bugs without me prompting them. If you’ve built “always-on” agents: what’s your cleanest wake-up + dedupe strategy?