[–] [S] 1 point 1 week ago (1 child)

You were right, so 2.3.7 has it: the setup guide now offers “Local model” 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.

  • source
  • parent
  • context
  • [–] [S] 1 point 1 week ago

    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 🙂

  • source
  • parent
  • context
  • [–] [S] 2 points 1 week ago

    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.

  • source
  • parent
  • context
  • [–] [S] 2 points 1 week ago* (last edited 1 week ago) (2 children)

    Update: you were right. Qwen3.8 27B (unsloth UD-IQ3_XXS) did the calculator task correctly (1234×5678 = 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.

  • source
  • parent
  • context
  • [–] 1 point 1 week ago

    It doesn't match the model's text. The check runs in the accessibility service on the actual button the tap would land on: its label, icon description and view id, as the app reports them. The model can write D E L E T E all it wants, the button still says Delete. It also can't tap Buddy's own approval card to approve itself.

    Where it can miss: a button with an odd or blank label, and apps you mark as trusted, where asking is left to the agent. And agreed, it's one guard, not the whole risk picture. Prompt injection from what's on screen is the bigger open problem, and the approval card is the backstop there.

  • source
  • parent
  • context
  • [–] [S] 2 points 1 week ago

    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.

  • source
  • parent
  • context
  • [–] 2 points 2 weeks ago

    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.

  • source
  • parent
  • context
  •  

    I've been building Buddy, a free, open source (Apache 2.0) Android app. You type or say what you want in a floating bubble, and an AI agent reads the screen, taps and types through your apps to do it.

    • Your choice of agent: Claude Code, Codex, OpenCode, Antigravity or Grok, running inside the app (Alpine Linux via proot) on your own plan. OpenCode's free models need no account.
    • No root, adb or PC: it reads the screen and taps through the accessibility service.
    • Asks first: before anything is sent, posted, bought or deleted. It pauses when you touch the screen and never types passwords or payment details.
    • Builds apps: with Linux tools on, it builds real APKs on the phone. This week I drew a maze on a paper towel, took a photo, and it made it a tilt game. The first build crashed on launch; it found the bug and fixed it.

    To be upfront:

    • What the agent reads on your screen goes to the AI service you pick.
    • It's early (2.2), tested most on a OnePlus 12 with Android 16.
    • 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.

    Source and releases: github.com/ghorbelhamdi/buddy-android

    Happy to answer questions here.

    view more: next ›