nanoMuse: An Open-Source Personal Agent for Every Device You Own

2026-10-06

AI Summary

This study addresses the limitations of existing personal intelligent agents, including the absence of cross-device long-term memory, insufficient auditability, and closed-source ecosystems. To overcome these challenges, this work proposes an open-source personal agent paradigm licensed under GPL-3.0. Methodologically, a relay mechanism is introduced to facilitate multi-device state synchronization and persistent proactive interactions. Furthermore, a novel Sentinel security framework combined with file-based traceable memory ensures operational auditability, while edge-side control interfaces and customizable model selection are seamlessly integrated. The project releases nanoMuse, a prototype system that provides cost estimations alongside a comprehensive roadmap encompassing memory modules, evaluation benchmarks, and open-source models. Ultimately, this paradigm effectively disrupts vendor-locked cloud ecosystems, establishing a transparent and extensible foundation for personal AI agents.

Abstract

Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country. Such an agent is expected to act on a person's accounts and devices, remember them across weeks, speak first when it is worth it, and answer for what it did. It is a kind of software, not a model, and until now had no open counterpart. This report defines the personal agent in five questions and three horizons. It reads how Muse is built from Meta's public record and a copy of its production prompt, each statement marked by its source. It then presents nanoMuse, the open-source counterpart under the GPL-3.0, one agent on every device a person owns, with hands on the phone's screen and the computer's. They share one conversation over a relay anyone can run; every action goes through a Sentinel, memory is files the person can read, and the model is their choice. Its size and cost are given as estimates. What is open, memory with provenance, an evaluation suite for the hands and an open model for them, is set out as a roadmap.

Problem

• Personal Agent
• Open-Source
• Cross-device
• Long-term Memory
• Closed-source Alternative

Innovation

• Personal Agent
• Open-Source
• Cross-device Control
• Sentinel Mechanism
• Transparent Memory