Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

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

Описание и применение

Создана 17‑агентная AI‑система, работающая полностью на Android‑устройстве без облака, реализующая совместное распознавание объектов и описание сцены.

Задача

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

Результат

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.

Рабочий процесс

  • 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.

Доказательства

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

Источник

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

Источник

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

Источник

  • Дата записи: 2026-10-08T08:41:27.788Z