# Pocket Crew: A Mixture-of-Agents Reasoning System Running on Flagship Smartphones

> Pocket Crew is an on-device AI reasoning system designed specifically for flagship smartphones, adopting the Mixture-of-Agents architecture. Multiple small models independently generate answer drafts, which are then evaluated and fused with the best logic by a synthesizer. It effectively controls memory usage through a sequential loading strategy, enabling high-quality local reasoning without an internet connection.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-03-31T12:15:43.000Z
- 最近活动: 2026-03-31T12:19:46.795Z
- 热度: 145.9
- 关键词: Mixture-of-Agents, on-device AI, mobile LLM, Android, local inference, privacy-preserving AI, smartphone AI, llama.cpp, edge computing, MoA
- 页面链接: https://www.zingnex.cn/en/forum/thread/pocket-crew-mixture-of-agents
- Canonical: https://www.zingnex.cn/forum/thread/pocket-crew-mixture-of-agents
- Markdown 来源: floors_fallback

---

## Pocket Crew: Introduction to the On-Device MoA Reasoning System for Flagship Smartphones

Pocket Crew is an on-device AI reasoning system designed specifically for flagship smartphones, using the Mixture-of-Agents (MoA) architecture. Its core features include: local operation without an internet connection, generating high-quality answers through multi-model collaboration; using a sequential loading strategy to control memory usage and adapt to smartphone resource constraints; all reasoning processes are completed locally to protect user privacy. This article will cover background, architecture, implementation, applications, and future prospects.

## Challenges of On-Device AI and Solutions from the MoA Architecture

With the improvement of smartphone computing power, on-device AI is evolving toward complex reasoning, but it faces the contradiction between model capability and memory/battery life. The Mixture-of-Agents architecture provides an innovative path: multiple small and medium-sized models independently generate answer drafts, and a synthesizer fuses the best logic, which not only improves quality but also uses resources efficiently. Pocket Crew is the practice of this idea on mobile devices, enabling local multi-model collaborative reasoning.

## Core Architecture and Memory Optimization of Pocket Crew

**MoA Pipeline**: Divided into draft generation (multiple models each generate answers with different focuses) and synthesis (the synthesizer evaluates and fuses the best logic). **Memory Optimization**: Uses a sequential loading strategy—models are loaded one by one, unloaded after generation, and only the synthesizer is kept in memory, solving the problem of smartphone memory limitations. **Privacy Protection**: All reasoning is completed locally, data never leaves the device, making it suitable for sensitive scenarios.

## Technical Implementation Details of Pocket Crew

**Native Android Development**: Based on the llama-android module ported from llama.cpp, using Kotlin language. Components include agents (collaboration logic), core (scheduling and memory management), and feature (UI). **Model Configuration**: Customize model sets and loading order via model_config.json; future support for BYOK mode (replace with cloud models). **ARM Optimization**: Integrate KleidiAI and Vulkan SDK for acceleration, using NEON instruction set to optimize computation.

## Application Scenarios and Value of Pocket Crew

1. **Privacy-Sensitive Scenarios**: For lawyers, doctors, etc., handling sensitive information, local reasoning eliminates the risk of cloud leakage; 2. **Offline Environments**: Usable on planes, subways, or remote areas (translation, guide summary, data processing); 3. **Daily Assistant**: Email writing, schedule planning, study tutoring—multi-model collaboration provides more comprehensive answers.

## Significance and Future Prospects of Pocket Crew

Pocket Crew represents the direction of on-device AI: improving effects through architectural innovation rather than scaling a single model. Its open-source nature supports community innovation (model combination, task optimization, IoT expansion). In the future, it will support BYOK mode and combine on-device and cloud collaboration; as smartphone computing power improves, it is expected to be popularized on more devices, making high-quality AI reasoning available on the go.