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

Описание и применение

Проблема: запуск многопользовательской системы ИИ на Android без облака. Решение: 17 специализированных агентов, работающих локально через Pyodide, LLaMA.cpp и 4‑битный Mistral 7B. Итог: работающий прототип, но медленный и ресурсоёмкий.

Задача

Running a multi‑agent system on a mobile device without cloud dependence, while maintaining privacy and resilience.

Результат

A proof‑of‑concept 17‑agent AI swarm runs on an Android phone, demonstrating local, distributed intelligence, but is slow, resource intensive, and occasionally crashes the device.

Рабочий процесс

• Install Termux and dependencies
• Set up Pyodide in a web view
• Download 4‑bit quantized Mistral 7B model
• Define agent personas in Python
• Implement generate_response and agent_interaction functions
• Create JavaScript sendMessageToAgent to bridge to Pyodide
• Load model and run agents in message‑passing loop
• Handle output flushing with sys.stdout.flush()
• Test agents with sample queries

Доказательства

I’ve been obsessively tinkering with running a multi‑agent system – a swarm of 17 individual AI “agents” – entirely on my Android phone.

Источник

Pyodide allows you to run Python inside a web browser, using WebAssembly (WASM).

Источник

I used a 4-bit quantized version of Mistral 7B.

Источник

This project was not easy. Here were the major hurdles: Performance, Memory Management, Pyodide Limitations.

Источник