I built a 17-agent AI swarm on my phone — here's how

说明与用途

在 Android 手机上完全本地运行的 17 代理 AI 群集，实现协作对象识别和场景描述，无需云端。

问题

Run a multi‑agent AI system for collaborative object recognition and scene description entirely on an Android phone without cloud dependency.

结果

A fully local, 17‑agent AI swarm capable of collaborative scene understanding runs on a single Android phone, demonstrating edge AI feasibility and emergent consensus behavior.

工作流

• 1. Quantize TinyLLM to 1.1B 4‑bit model with llama.cpp.
• 2. Deploy MobileNetV2 TFLite for object detection.
• 3. Define 17 agents with distinct roles and prompts.
• 4. Use Tasky to queue tasks and distribute to agents.
• 5. Agents process image data and generate partial outputs.
• 6. Consensus agents aggregate results into final description.
• 7. Run entire pipeline on Pydroid 3 on Android.
• 8. Monitor memory usage and optimize resource allocation.

证据

I’m using a 1.1B parameter version of TinyLLM, quantized down to 4‑bit precision using llama.cpp.

来源

Leveraging a pre‑trained MobileNetV2 model (using TensorFlow Lite), these agents identify objects within the image

来源

Tasky is my custom system for orchestrating the agents. Think of it as a task queue and communication bus.

来源