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

Описание и применение

Создана система из 17 специализированных агентов на Android‑устройстве, использующая локальные LLMs для сбора, анализа, проверки и суммирования информации о веб‑трендах.

Задача

Run a multi‑agent AI swarm on a mobile device to autonomously gather, analyze, validate, and summarize information about a specific topic.

Результат

Successfully ran 17 quantized LLM agents on a Pixel 7, achieving decentralized information gathering and summarization with acceptable performance, battery usage, and resilience.

Рабочий процесс

• 1. Deploy Redis locally for task queue
• 2. Start coordinator agents to push scrape tasks
• 3. Scraper agents fetch URLs, parse HTML, limit text to 4000 chars
• 4. Analyzer agents perform sentiment, topic extraction, key phrase identification using llama.cpp with Mistral 7B Q4_K_M
• 5. Validator agents cross‑reference data, flag misinformation
• 6. Summarizer agents compile analyzed data into report
• 7. Coordinators collect results, manage retries, handle failures

Доказательства

Running 17 LLMs, even quantized ones, on a phone is challenging.

Источник

I chose a quantized version of Mistral 7B (specifically Q4_K_M) for its balance of performance and size.

Источник

Task Queue (Redis): A Redis server running locally on the phone (using a lightweight Redis implementation) acts as a task queue.

Источник

SQLite is used for persistent storage of scraped data, analysis results, and agent logs.

Источник