# Gemini CLI

Published articles for Gemini CLI.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Android CLI meet Gemini CLI

DevFeed: [Android CLI meet Gemini CLI](<https://devfeed.tech/articles/android-cli-meet-gemini-cli-32034.md>)

Original publisher: [Read original article](<https://www.maiatoday.net/p/android-cli-meet-gemini-cli/>)

Published: 2026-04-18T19:20:59Z

Content type: tutorial

Language: en

Sources: [maiatoday](<https://devfeed.tech/sources/maiatoday.md>)

Topics: [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Android skills](<https://devfeed.tech/topics/android-skills.md>), [Emulator](<https://devfeed.tech/topics/emulator.md>), [Testing](<https://devfeed.tech/topics/testing.md>), [Android Studio](<https://devfeed.tech/topics/android-studio.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [android](<https://devfeed.tech/tags/android.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [cli](<https://devfeed.tech/tags/cli.md>), [emulator](<https://devfeed.tech/tags/emulator.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

This tutorial introduces Android CLI and matching agent skills for Gemini CLI and other agents. It covers installation, initialization, Android knowledge-base access, emulator interaction, and testing workflows with screenshots and interactions.

### Source excerpt

In recent Android AI experiments I always felt I missed something. If I was in the IDE using an agent with Gemini in Android Studio, I loved the access to the knowledge base and the special tools but I could only spin up one instance. If I was in my <insert favourite CLI agent tool> let's say gemini-cli, I missed the quality of life improvements that made me have to jump back into the IDE. Yes I could install an adb extension into gemini-cli or write some custom skill to try to achieve what I wanted or paste a bunch of Android official urls into the prompt. It was always fiddly to open the IDE from a worktree or test from an orchestrator session. As of last week there is a new tool and a bunch of matching skills that solve this. Android CLI NOTE I see 2 main benefits of using android-cli easy access to accurate android knowledge base that is agent friendly and will reduce token use easy emulator interaction and improved testing and iteration with screenshots and interactions How do I get it The installation is pretty simple, follow the Android cli docs TLDR; Download and install make sure you are using the new android executable not the old one, type which android and you are looking for something like /usr/local/bin/android If not then check your path setup. Or ask an agent to do it with this prompt. read the file that sets up my path and modify it such that the android sdk paths are not added in the the beginning but at the end of the path. I need this because the path `/usr/local/bin` is in the path before the android sdk and it needs to be first run android init to make sure all agents on your system will use this tool. It sets up a skill for claude, gemini and more optionally install all the skills created for this tool android skills add --all Show me some cools things I can do with it I am going to use a repo with a demo app I built with Gemini in Android Studio to take it for a spin. This app is a simple mood tracking app. You don't need to try it on my app,

## Github Copilot vs Google Antigravity

DevFeed: [Github Copilot vs Google Antigravity](<https://devfeed.tech/articles/github-copilot-vs-google-antigravity-29079.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/github-copilot-vs-google-antigravity>)

Author: Alex Ewerlöf

Published: 2026-03-22T23:19:06Z

Content type: comparison

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>), [Google](<https://devfeed.tech/topics/google.md>), [Chrome](<https://devfeed.tech/topics/chrome.md>)

Tags: [browser](<https://devfeed.tech/tags/browser.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [google](<https://devfeed.tech/tags/google.md>), [google-antigravity](<https://devfeed.tech/tags/google-antigravity.md>)

### AI overview

A firsthand comparison of GitHub Copilot and Google Antigravity based on the author's experience using both tools. The article describes Antigravity's browser integration and Plan mode, while noting that its newer product maturity is visible compared with Copilot.

### Source excerpt

Why Github gets developers and why it's hard to tell who Antigravity is for

## Android ❤ Gemini CLI - tech debt detection Code Maat skill

DevFeed: [Android ❤ Gemini CLI - tech debt detection Code Maat skill](<https://devfeed.tech/articles/android-gemini-cli-tech-debt-detection-code-maat-skill-32033.md>)

Original publisher: [Read original article](<https://www.maiatoday.net/p/android-%EF%B8%8F-gemini-cli-tech-debt-detection-code-maat-skill/>)

Published: 2026-03-08T00:00:00Z

Content type: tutorial

Language: en

Sources: [maiatoday](<https://devfeed.tech/sources/maiatoday.md>)

Topics: [Android](<https://devfeed.tech/topics/android.md>), [Tech Debt](<https://devfeed.tech/topics/tech-debt.md>), [Agent Skill](<https://devfeed.tech/topics/agent-skill.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Code](<https://devfeed.tech/topics/code.md>), [Git](<https://devfeed.tech/topics/git.md>), [Android Studio](<https://devfeed.tech/topics/android-studio.md>)

Tags: [adb](<https://devfeed.tech/tags/adb.md>), [agent-skill](<https://devfeed.tech/tags/agent-skill.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android](<https://devfeed.tech/tags/android.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [code-maat](<https://devfeed.tech/tags/code-maat.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [git](<https://devfeed.tech/tags/git.md>), [tech-debt](<https://devfeed.tech/tags/tech-debt.md>)

### AI overview

This tutorial explores using Gemini CLI and an agent skill with Code Maat to identify technical-debt hotspots in the Habitica Android codebase. It describes using Git history to analyze file churn and logical coupling, and compares the approach with the Gemini Agent in Android Studio.

### Source excerpt

Introduction What AI tools work for building Android apps? I am exploring some variations. In this post I will look at Gemini CLI, tech debt detection with a skill using Code Maat and how this compares with the Agent of Gemini in Android Studio. I am not starting with a new project. What if you have an existing codebase and you want to find the best place to tackle some tech debt that will make a difference for everyone. The sample codebase is the Habitica app, which had its first commit in 2015. Rather than poking at the code in a random or an "intuitive" way or asking the AI questions, let's look at a more deterministic way to answer this question. Or rather, let's teach the agent to use some scripts to answer this question. The benefit of packaging this functionality in a skill is that you can create this specialisation and script usage in a skill that will be loaded lazily only when you need it. The theory - Code as Crime scene Adam Tornhill wrote a book, Your Code as a Crime Scene, that uses your git history and applies forensic science to figure out where the hotspots, logical coupling, churn and more can be found in your code base. He has a java tool called Code Maat that you can use to analyse this information. The problem is, it is a bit finicky to setup and run and I can never remember all the command line parameters for git or for the tool. The theory TLDR is if you can see which large files change often or which files always change together, you can see which parts of your code are brittle or are coupled. The added benefit is that this analysis is language neutral. So if you build an agent skill for this, it can be used on any codebase. Creating the Code Maat Skill What do we need the link to Code Maat optionally download the code-maat standalone jar and put it in ~/tools/code-maat.jar to speed up the first run Gemini CLI + authentication and API key if you have it the skill-creator skill - this is part of the Gemini CLI install the Habitica Android app

## Using Gemini CLI and the Obsidian CLI to manage note metadata

DevFeed: [Using Gemini CLI and the Obsidian CLI to manage note metadata](<https://devfeed.tech/articles/from-cli-to-cli-gemini-and-obsidian-32053.md>)

Original publisher: [Read original article](<https://www.maiatoday.net/p/from-cli-to-cli-gemini-and-obsidian/>)

Published: 2026-02-21T20:33:17Z

Content type: article

Language: en

Sources: [maiatoday](<https://devfeed.tech/sources/maiatoday.md>)

Topics: [Obsidian](<https://devfeed.tech/topics/obsidian-md.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Script](<https://devfeed.tech/topics/script.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [Markdown](<https://devfeed.tech/topics/markdown.md>), [Git](<https://devfeed.tech/topics/git.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [automation](<https://devfeed.tech/tags/automation.md>), [cli](<https://devfeed.tech/tags/cli.md>), [docs](<https://devfeed.tech/tags/docs.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [git](<https://devfeed.tech/tags/git.md>), [knowledge-management-systems-metadata](<https://devfeed.tech/tags/knowledge-management-systems-metadata.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [obsidian](<https://devfeed.tech/tags/obsidian.md>), [script](<https://devfeed.tech/tags/script.md>)

### AI overview

The author describes using Gemini CLI with the Obsidian CLI, along with shell tools and scripts, to analyze and standardize metadata across an Obsidian vault. The work covered status values, Type and ContentType properties, tags, documentation, and validation scripts for future consistency checks.

### Source excerpt

Let's talk about the "Obsidian Paralysis." For a while, I've been using Obsidian to jot down ideas, plan content, and collect those random snippets from the internet that feel like digital gold. I moved over from Notion a while back. The freedom of simple Markdown managed by Git was liberating. Pure, texty goodness. But--and there's always a but, isn't there?--one thing always held me back. That nagging little voice: Am I doing it right? I know, I know. The "experts" say just write the notes and let the system emerge organically. But I was forever second-guessing myself. Is this a status: NotStarted or status: not-started? Is the type a "thought" or a "note"? I was spending more time fiddling with the taxonomy and the metadata "meta-system" than actually creating content. But today, everything changed. I opened Obsidian and saw the news: they now have a CLI interface. 💡: "What if I introduced the Obsidian CLI to an AI Agent CLI?" For my experiments, I called in Gemini CLI. I basically sat them down in a terminal together, let Gemini CLI figure out what the Obsidian CLI could do, and then--with a spicy mix of grep, sed, awk, and the new Obsidian commands, we went to work. Here's the "Metadata Makeover": 1. The Status Cleanup I had Gemini pull every single Status property from every note in my vault to analyze them for consistency. It detected patterns I didn't even know I had (like all the versions of Idea Ideas Research researching). We cleaned up the mess, documented the new "Golden Rules" for statuses, and Gemini wrote a validation script that I can run that will clean things up or highlight inconsistencies. 2. The "Type" vs. "ContentType" Tangle We did the same for Type and ContentType. It turns out I was using them interchangeably like a chaotic neutral character. Gemini helped me settle on a single source of truth, updated my docs, and tweaked the validation script to keep things tidy. 3. The Tag Jungle We looked at everything--frontmatter tags, in-document hashtag

## Running Gemini CLI in a Docker container

DevFeed: [Running Gemini CLI in a Docker container](<https://devfeed.tech/articles/running-gemini-cli-in-a-docker-container-27729.md>)

Original publisher: [Read original article](<https://gagor.pro/2025/10/running-gemini-cli-in-a-docker-container/>)

Author: Tom

Published: 2025-10-31T00:00:00Z

Content type: tutorial

Language: en

Sources: [Tomasz Gągor](<https://devfeed.tech/sources/tomasz-gagor.md>)

Topics: [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [Docker Container](<https://devfeed.tech/topics/docker-container.md>), [Node.js](<https://devfeed.tech/topics/node-js.md>), [Bash](<https://devfeed.tech/topics/bash.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [bash](<https://devfeed.tech/tags/bash.md>), [cli](<https://devfeed.tech/tags/cli.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-container](<https://devfeed.tech/tags/docker-container.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [github](<https://devfeed.tech/tags/github.md>), [guide](<https://devfeed.tech/tags/guide.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [linux](<https://devfeed.tech/tags/linux.md>), [macos](<https://devfeed.tech/tags/macos.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [npm](<https://devfeed.tech/tags/npm.md>), [shell](<https://devfeed.tech/tags/shell.md>), [zsh](<https://devfeed.tech/tags/zsh.md>)

### AI overview

A practical guide to running Google's Gemini CLI in a Docker container instead of installing Node.js and its dependencies directly. It explains the author's custom Docker image, weekly updates, shell integration, configuration persistence, permissions, and interactive usage.

### Source excerpt

Learn how to run Google's Gemini CLI in a Docker container to avoid installing Node.js and its dependencies directly on your system. This guide provides a simple setup, a recommended shell function for seamless integration, and usage examples.

## Using Gemini CLI as an AI Coding Copilot

DevFeed: [Using Gemini CLI as an AI Coding Copilot](<https://devfeed.tech/articles/my-co-pilot-is-an-ai-agent-and-it-s-a-game-changer-26126.md>)

Original publisher: [Read original article](<https://medium.com/@yonatanvlevin/my-co-pilot-is-an-ai-agent-and-its-a-game-changer-c1118bb90245?source=rss-8735065c2497------2>)

Author: Yonatan (Yoni) Levin

Published: 2025-06-25T15:27:03Z

Content type: opinion

Language: en

Sources: [Stories by Yonatan V. Levin on Medium](<https://devfeed.tech/sources/stories-by-yonatan-v-levin-on-medium.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [genai](<https://devfeed.tech/topics/genai.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [co-pilot](<https://devfeed.tech/tags/co-pilot.md>), [devtools](<https://devfeed.tech/tags/devtools.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [genai](<https://devfeed.tech/tags/genai.md>), [llm](<https://devfeed.tech/tags/llm.md>)

### AI overview

The author introduces an opinion piece about using Gemini CLI for software development, drawing on work at a startup that uses LLMs and other AI technologies.

### Source excerpt

After a long break and a lot of life happening all at once, I'm back. Why? Because so much exciting stuff has happened that I just need to spit it out. It's going to be a long article, so prepare a good cup of coffee & a couple of cookies. Today, we're diving deep into something that I believe is the future of how we build software: the Gemini CLI. At least, until the next amazing thing comes along and reshapes our industry all over again. :) The Backstory: A New Mission and a Brick Wall For those who don't know me, my name is Yonatan, but friends call me Yoni. My career has been a wild ride: from low-level hardware development to leading Android teams, then switching to the backend to build the Public API for monday.com, and finally, leading AI development with the explosion of GenAI. Someone once joked that my career is just a series of abbreviations: Android -> API -> AI. About a year ago, after an incredible six-year journey, I left monday.com. After taking some time to breathe, I teamed up with two amazing people, Limor and Eyal, to start a new adventure: a startup called Wisdom. Our mission is to help people become wiser and happier by transforming how they interact with the profound knowledge tucked away in self-development books. We want to transform passive reading into an active, life-changing experience, bridging the gap between knowing something and truly living it. A few weeks ago, we launched our first closed alpha version with a chosen book authors. Our tech stack is a beast: various LLMs, Knowledge Graphs, audio models, and a ton of custom heuristics. And, of course, the standard stuff -- Node.js servers and React for our websites. We started, as most do, with a prototype. Something to show investors and our first potential customers. But I hit a brick wall. Hard. Despite my vast experience, my front-end knowledge was practically zero. I knew some basic HTML and CSS, but that was it. How was I, a backend and AI guy, supposed to build the face of our pro