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.

  • Canuck@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    8
    arrow-down
    7
    ·
    edit-2
    10 days ago

    Excellent for local models running via OpenCode and helping with UAT on Android. Well done. What else is on your roadmap for this? Will you support Watch/TV/XR? F-Droid might take this.

    • ghorbelhamdi@lemdro.idOP
      link
      fedilink
      English
      arrow-up
      4
      arrow-down
      4
      ·
      10 days ago

      Thanks, and thanks for the crosspost! Local models already work: in Settings you can add a custom OpenAI-compatible address (llama.cpp, Ollama or LM Studio on your network) and use it with OpenCode. It works best with models that are good at tool calling, since everything goes through phone tools.

      Other devices: it’s built for phones, but someone already forked it to run on a Nintendo Switch with Android, with Joy-Con navigation: https://github.com/Lendss/buddy-switch. So other Android devices are clearly possible, I just haven’t tested watches, TVs or XR myself.

      F-Droid: good timing. Buddy now builds all its native parts (proot, talloc and friends) from source in CI, with no prebuilt binaries in the repo, which was the main thing in the way. So an F-Droid build should be doable now. Until then, releases are on GitHub and the app updates itself.

      • Shatur@discuss.tchncs.de
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        1
        ·
        10 days ago

        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!

        • ghorbelhamdi@lemdro.idOP
          link
          fedilink
          English
          arrow-up
          3
          arrow-down
          2
          ·
          edit-2
          10 days ago

          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.

          • Shatur@discuss.tchncs.de
            link
            fedilink
            English
            arrow-up
            3
            arrow-down
            1
            ·
            10 days ago

            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).

            • ghorbelhamdi@lemdro.idOP
              link
              fedilink
              English
              arrow-up
              2
              ·
              edit-2
              9 days ago

              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.

              • Shatur@discuss.tchncs.de
                link
                fedilink
                English
                arrow-up
                2
                ·
                edit-2
                9 days ago

                Yeah, 27B only usable if you can fit it entirely in VRAM. Only MoE models are fine to split, like the mentioned Qwen 3.8 Flash Next. Even though it’s large, only the active 6B parameters needs to be located in VRAM, the rest can be in RAM and SSD.

                • ghorbelhamdi@lemdro.idOP
                  link
                  fedilink
                  English
                  arrow-up
                  2
                  ·
                  8 days 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.

        • Shatur@discuss.tchncs.de
          link
          fedilink
          English
          arrow-up
          4
          arrow-down
          1
          ·
          10 days ago

          Nice to hear!

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

            • Shatur@discuss.tchncs.de
              link
              fedilink
              English
              arrow-up
              2
              ·
              3 days ago

              I tried it out, during setup I don’t see a way to select an OpenAI compatible provider. Is this an older version?

                • Shatur@discuss.tchncs.de
                  link
                  fedilink
                  English
                  arrow-up
                  2
                  ·
                  3 days ago

                  Ah, I see. Maybe it would make sense to allow users to select the option like llama.cpp from the start? In Zed editor, for example, Llama.cpp is one of the “providers”.

                  After adding it, I still see “Install Claude Code” as one of the setup steps. Do I still need to install it?

                  Sorry for not trying it earlier, I was quite busy last week 🙂

                  • ghorbelhamdi@lemdro.idOP
                    link
                    fedilink
                    English
                    arrow-up
                    1
                    ·
                    3 days ago

                    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.

                  • ghorbelhamdi@lemdro.idOP
                    link
                    fedilink
                    English
                    arrow-up
                    1
                    ·
                    3 days 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 🙂