Fair point. You do still need one agent, since it's what talks to the model. For local I'd use OpenCode (free, no account); Codex works too. Set Default brain to OpenCode in Settings, install it, and pick your llama.cpp model in a chat. No need for Claude Code, that step only shows because it's the default agent. Thanks for trying it ๐
It's not in the first-run setup, it's in Settings โ API keys โ Add API key. Pick Ollama, LM Studio or llama.cpp from the Service menu (or Custom for any other OpenAI-compatible address), put in your server's address and leave the key empty. Then use it in an OpenCode chat. The 2.3.1 on F-Droid has it. More here: https://github.com/ghorbelhamdi/buddy-android#local-models
@Shatur@discuss.tchncs.de as promised: Buddy is on F-Droid now ๐ https://f-droid.org/packages/app.buddy.assistant/ It's at 2.3.1 there for now, newer versions follow as F-Droid builds them.
Good call. Qwen3.6 35B-A3B runs fine split between my 8 GB card and RAM, and gets the task right. Flash Next is too big for 32 GB. The latest Buddy (2.2.27) also fixes local models with Codex, which your suggestion helped me find.
Update: you were right. Qwen3.8 27B (unsloth UD-IQ3_XXS) did the calculator task correctly (1234ร5678 = 7,006,652), but took 18 minutes on my 8 GB card, almost all of it reading the prompt and screen on the CPU.
Qwen3.5 9B is the interesting one: one run typed the wrong numbers and claimed success, the next did it right in about 2 minutes. So small models can do it, just not reliably yet.
I did appeal. Google's answer, word for word: "the app utilizes the accessibility API for performing autonomous actions... The accessibility API is not designed and cannot be requested for performing autonomous tasks." So the problem was the agent acting on its own, not which AI services it uses.
The accessibility-tool exception is only for apps built mainly for people with disabilities. Buddy can help there, but it does a lot more, so claiming that wouldn't be honest. If anyone has gotten an agent app like this through review, I'm open to trying again.
Curious too. In my tests Qwen3 4B and 8B handled one-step requests but fumbled multi-step ones (tapped the wrong buttons, then said it worked). gpt-oss 20B did better but was inconsistent: one run got a 2-step task right, the next claimed a tool didn't exist. I haven't tried a 27B yet, and I don't know if it'll even run usably on my RTX 2060 Super (8 GB). If anyone runs one through Ollama or llama.cpp, I'd love to hear how it does.
I'm not your friend, pal ๐
Fair to be skeptical, but it isn't the model being asked nicely. Buddy checks every tap itself: when the button is Send, Post, Buy, Pay, Delete and similar (by its label or id, in several languages), Buddy stops and shows an approval card, whatever the model wants. It's a word list, so an oddly named button can slip through; it's all in Guard.java if you want to look: https://github.com/ghorbelhamdi/buddy-android/blob/main/app/src/main/java/app/buddy/assistant/Guard.java
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 (4โ8B) handle simple requests but fumble multi-step tasks on the screen, so you'd want a bigger model for real use.
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
ghorbelhamdi
0 post score0 comment score
You were right, so 2.3.7 has it: the setup guide now offers โLocal modelโ from the start. It sets up OpenCode, asks for your llama.cpp / Ollama / LM Studio address and makes that the default. It's on GitHub now, F-Droid follows in a few days.