I have the fairphone 6 with CalyxOS. Not as good as graphene but good enough for my usecase. Would recommend.

Guess what? An SD card slot so you don't have to rely on cloud storage and streaming services like with graphene on a pixel!

Jesus Christ

Any open-source alternatives, or something degoogled?

Give me a small and light weight Android phone with relatively modern specs.

I have used a CGM for years now, but I don't know all of the models - only a few of them. In my experience most of the time the manufacturer offers some kind of cloud service to store your data (given your cousin is using a device that is capable of transmitting said data) and there are free to use services like Glooko (it's the one I use - there are others) you can connect different devices to store and visualize these data. It helps a lot exploring patterns and finding ways to improve my therapy.

Nice to hear!

Please, ping me once you get the approval, I prefer F-Droid over Obtainium 🙂

It's is expected, they're small models. But something like Qwen 3.8 27B or Qwen 3.8 Flash Next should handle it.

How much VRAM do you have? If it's a 12GB card and you also happens to have 64 GB of RAM, you should be able to run Qwen 3.8 Flash Next with Q3. It's one of the most "hyped" local models right now (because it's quite capable and has somewhat realistic HW requirements).

I'm not your friend, pal 😄

It can now: since 2.2.25 it works with your own model server (Ollama, LM Studio or llama.cpp) on your network or over Tailscale, with no key, and nothing goes to an AI company. Honest caveat: small models (4–8B) handle simple requests but fumble multi-step tasks on the screen, so you'd want a bigger model for real use.

Youre god damn right it does.

Something wrong with the old voice access?

I'd be worried something as unpredictable as an LLM would put more disabled users in danger that it would help.

If the backdoor was intentional, you could see it as donating compute resources to the devs token maxing addiction

are you familiar with CGMs? My 8 yo cousin has got one but it's active only fir 14 days and when it deactivates, It wipes all the data (wtf?). Is tyere a way to keep the data? Does it depend on the model?

I ain't your buddy, friend.

The safety versus privacy dilema is not something I saw coming. I don't like it.

Done: 2.2.25 makes this easy. Ollama, LM Studio and llama.cpp are in the service list, plain http works on your own network and over Tailscale, and no key is needed. README has a section now: https://github.com/ghorbelhamdi/buddy-android#local-models

Honest results so far, on a PC with an RTX 2060 Super: Qwen3 8B and 4B handle simple one-step requests (battery, phone status), but multi-step tasks on the screen failed. The 4B tapped the wrong buttons in the calculator and then claimed it worked. So for real tasks you'll want a bigger model; I'm trying gpt-oss 20B next.

Update: it's now submitted to F-Droid, with reproducible builds, so the F-Droid and GitHub versions will be the same app signed with the same key, and you can switch between them: https://gitlab.com/fdroid/fdroiddata/-/merge_requests/56198

It's not on Play (Google rejected the accessibility use)

And rightly so. Stop making me side with Google.

Maybe if it were designed to run completely locally I could respect it.

It's not much, but I would say pretty much everyone who uses some kind of continuous glucose measurement has a more powerful tool provided by the manufacturer or an open source alternative. The feature is pretty basic in Google Health anyways (it just shows the data), but at least it now is usable by anyone and not just those who happen to use the same units as Google. It opens it up to new integrations.

The misleading title isn't exactly helping

I ain't your pal, Buddy.

Local models already work: in Settings you can add a custom OpenAI-compatible address (llama.cpp, Ollama or LM Studio on your network)

You should've mentioned this in the readme 🙂 I'll check it out!

groundbreaking

You can finally change the unit of blood glucose measurements.

For those not into this matter: There are two units of measurement that can be easily converted into each other (simple multiplication). But previously Google Health was limited to the one more prevalent in the US - now you can switch.

It's not on Play (Google rejected the accessibility use), so it's an APK from GitHub releases, built by GitHub Actions from the source.

Did you explain its use as an accessibility aid being its core feature for differently abled people? If you have explained that as a core feature google could've budged. You would've needed to limit the API to select few like OpenAI, Gemini, Claude with additional guardrails and use reporting. But, it could've been accepted by google.