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

Автор создал 17‑агентный AI‑сверм на Pixel 7, полностью работающий локально без облака, используя TensorFlow Lite, SQLite и многопоточность Python.

Задача

Running a multi‑agent AI system entirely on a mobile device without cloud or API reliance, while maintaining performance and fault tolerance.

Результат

The author successfully ran a 17‑agent AI swarm on a Pixel 7, achieving efficient local routing for logistics scenarios without cloud dependency, demonstrating feasibility of on‑device multi‑agent systems.

Рабочий процесс

  • Train agents on a powerful machine using synthetic map data and reward‑based training.
  • Convert Keras models to TensorFlow Lite with post‑training quantization to reduce size and improve speed.
  • Deploy quantized models to the Pixel 7 and load them with Python.
  • Store map data and agent memory in a local SQLite database.
  • Create 17 agents (map sensor, urgency assessment, route evaluation, route coordinator, environmental update) each as a Python thread.
  • Implement a central message broker using a Python queue for inter‑agent communication.
  • Agents publish outputs as JSON messages to the queue; subscribers consume relevant data.
  • Route coordinators aggregate evaluations and select final routes based on urgency, distance, and risk.
  • Run the swarm continuously, updating environmental data and re‑evaluating routes as obstacles change.
  • Monitor performance and iterate on model size and threading to maintain responsiveness.

Доказательства

I’ve managed to get a 17-agent swarm up and running on my Pixel 7, and it’s surprisingly capable.

Источник

Training these agents was done on a more powerful machine, naturally.

Источник

I used post‑training quantization in TensorFlow Lite:

Источник

I used Python's threading module to run each agent in its own thread.

Источник

  • Дата записи: 2026-10-09T07:40:57.008Z