Open Minis: New AI Agent for Smartphones with Open Source Code
Open Minis: New AI Agent for Smartphones with Open Source Code
Open Minis has introduced an AI agent for smartphones with open source code, allowing users to customize it to their needs.
The terminal on the phone turned out to be insufficient. Therefore, they added an AI agent ✋
Open Minis has been refining it in closed mode for several months, and now they have fully opened the source code of the application for iOS and Android.
Inside is a Linux shell, browser control, Skills, persistent memory, and access to smartphone capabilities. In other words, it’s practically a ready-made foundation for your own mobile AI agent.
The project is already used by tens of thousands of people, and now it can be forked on GitHub and customized to your liking.
Why it matters
AnalysisThis project opens up new opportunities for developers looking to create their own AI agents. The open-source nature allows for customization to meet individual needs.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Working with Git via Claude Code: A Beginner's Guide
A complete hands-on guide to Git integration in Claude Code: smart staging, automated commit messages, merge conflict resolution, GitHub CLI, and safety guardrails.
Four Resume Tips from OpenAI’s Head of Applied AI Development
Wulfie Bain, OpenAI’s head of applied AI development, shared four resume rules: keep it short, remove irrelevant details, highlight outcomes, and lead with the strongest achievements.
AI Radar: GPT-6.1 Terra, Gemini 4 Carbon, Mistral Large 4 and OpenAI/Anthropic pricing changes
A roundup of recent AI news: new LLM releases, OpenAI and Anthropic subscription changes, world models, video generation, and research updates.
JSON — Structured Data for Programs, APIs, and AI Agents
A complete hands-on guide to JSON: syntax specifications, serialization via parse and stringify, REST API consumption, JSON Schema validation, and structured outputs for LLMs.