Screenshots Why CLI Features AI Agent Phone Mesh Integrations Games FAQ Docs Built Today Contact Download APK
v10.2.0 — AI Agent System + Screen Agent + Browser Agent

A full development environment
on your phone.

Not a remote desktop. Not a web IDE. A real native Linux environment running directly on your phone's hardware. Compile Android apps with Gradle, deploy to Vercel, send SMS from scripts, take photos from the command line, run AI agents that answer your calls while you sleep. Connect multiple phones into a mesh network. 80 Android permissions, 90+ hardware commands, 22+ built-in platform CLIs. One APK, no laptop, no server.

How It Works
Claude Code AI running inside MobileCLI with 8 terminal sessions

Real screenshots. Not mockups.

Every screenshot below was taken on a Samsung Galaxy S24. This is what MobileCLI actually looks like.

AI Camera Vision analyzing a beach photo in MobileCLI web chat
Camera + AI Vision

Take a photo — AI sees and describes it in real time

Claude Code AI with Opus 4.6 running inside MobileCLI
Claude Code

Anthropic's AI — Opus 4.6, Claude Max, 8 sessions

Gemini CLI with Gemini 2.5 running inside MobileCLI
Gemini CLI

Google's AI — Gemini 2.5, ready to code

OpenAI Codex CLI with sign-in options
Codex CLI

OpenAI's AI — use your subscription or API key

MobileCLI navigation drawer showing settings and AI tools
One-Tap Access

Settings, sessions, and every tool from the drawer

22 platform CLIs listed in MobileCLI's drawer menu
22 CLIs Built In

GitHub, Vercel, Firebase, Supabase, Godot, and more

GitHub CLI authentication flow
Real Authentication

Full OAuth — not API tokens, real verified sessions

Three steps to your pocket dev machine

1

Download & Install

Download the APK. Open it. A setup wizard extracts a full Linux filesystem, installs Python, Node.js, Git, Java 17, Gradle, and 22+ platform CLIs — Claude, Gemini, Codex, GitHub, Vercel, Firebase, Godot, Twilio, and more. About 5 minutes, fully automatic.

2

Choose Your AI

Launch Claude, Gemini, or Codex from the menu. They can read your files, write code, run commands, and deploy — all from the terminal. Use your existing subscription or API key.

3

Build Anything

Android apps, websites, games, AI agents, bots, APIs. Deploy to Vercel, Firebase, GitHub Pages. The same tools professionals use on their laptops, in your pocket.

The most powerful interface on a phone

Most mobile dev tools are simplified apps, toy IDEs, or remote connections to a real computer. MobileCLI is the real thing — a native environment that runs entirely on your device.

Security

Most Secure Interface

Log into GitHub, Vercel, Firebase, Heroku, Netlify, and dozens more with full authenticated sessions — not limited API tokens, not browser cookies. Real OAuth, SSH keys, and encrypted connections. Your credentials stay on your device. No middleman. No third-party servers.

Cost

Your Money Goes Further

Use your existing Claude Max, ChatGPT Plus, or Gemini subscription — or pay API pricing for exactly what you use. Either way, you get 100% of the AI's capabilities, not the limited web version. Three AI assistants, one device, your choice of plan.

3 AIs • Your plan • Full power
Power

100% of Every Tool

Mobile apps give you 10% of what a service can do. The CLI gives you 100%. Every feature, every flag, every option — nothing hidden behind a GUI. When you log into GitHub from the CLI, you can do everything — not just what an app decides to show you.

Extensibility

Install Anything

There is no ceiling. No locked features. No "upgrade to pro." The entire environment is yours. Install PostgreSQL, Redis, nginx, Rust, Go, Ruby. Compile from source. Write your own tools. If it runs on Linux, it runs here.

1,500+ packages • 2M+ npm • 500K+ pip
What You Can Build

Build anything. On your phone.

Everything below happens locally. No remote servers. No cloud VMs. Your phone is the computer.

📱

Build Android Apps

Java 17, Kotlin, Gradle, aapt2, d8, apksigner — the full Android build toolchain runs natively on your phone. Write code, compile, sign, and install APKs without ever touching a computer. MobileCLI itself was built this way. The AI inside the app modified the app's source code, compiled a new APK, and handed it back. On a phone.

🌐

Deploy Live Websites

Type vercel --prod and your site is live in 10 seconds. The website you're reading right now — mobilecli.com — is designed, updated, and deployed entirely from this phone. React, Next.js, static sites, serverless functions. Vercel, Firebase, Netlify, Fly.io, Heroku. Real production deployments with real domains.

🤖

AI That Codes For You

Claude Code (Anthropic), Gemini CLI (Google), and Codex CLI (OpenAI) are all pre-installed. These aren't chatbots — they're autonomous coding agents. They read your entire project, write code across multiple files, run tests, fix errors, commit to Git, and deploy to production. In one session today, Claude wrote 2,969 lines of Python, a 525-line Kotlin Android activity, and deployed a full website — with zero errors.

📦

Full Git Workflow

The GitHub CLI gives you everything. Clone repos, create branches, commit, push, open pull requests, review code, manage issues, create releases with attached binaries. Authenticated with real OAuth — not a limited token. The developer behind MobileCLI manages 66 private repositories entirely from this phone.

🎮

Create Games

Godot 4 game engine included. Build games and export to Android, iOS, Web, Windows, Mac, or Linux. Full game development, from concept to published app, on your phone.

📡

Control Your Phone's Hardware

90+ commands that turn your phone into a programmable device. sms-send sends a real text. camera-photo fires the camera. location returns GPS coordinates as JSON. sensor -s accelerometer reads motion data. infrared-transmit controls your TV. torch on turns on the flashlight. fingerprint triggers biometric auth. Every command returns structured JSON. Every one is scriptable.

🗄

Run Real Databases

PostgreSQL, MariaDB, Redis, SQLite — actual database servers running on your phone. Real databases for real development. Not cloud-only managed services.

Self-Modification

This is the one that breaks people's brains. AI running inside MobileCLI can clone the app's own source code, modify the Kotlin, recompile with Gradle, sign a new APK, and hand it to you. The app literally rebuilds itself. MobileCLI has gone through 30+ versions this way — each one built by AI running inside the previous version, on a phone, with no computer involved at any point.

Your phone becomes an AI agent

MobileCLI isn't just a terminal. It's a full AI agent with a SecurityEngine, 9 skill engines, 9 communication gateways, a 14-screen web console, and an always-on daemon. Screen Agent reads and controls any Android app through accessibility. Browser Agent injects an AI overlay on any web page. Vision analyzes screenshots with Claude. The agent monitors texts, answers calls, controls hardware, and runs autonomously — all on your phone.

How the agent works

The agent runs as a background daemon. It polls your communication channels every few seconds — checking for new SMS messages, Twilio calls, Telegram messages, Discord pings. When something comes in, it routes the message through an AI brain that understands context, channel constraints, and your preferences.

The brain supports multiple AI models. Claude Sonnet is the default. If Claude is unavailable, it falls back to Gemini automatically. The brain is channel-aware: it knows SMS caps at 160 characters, WhatsApp allows 4,096, Discord allows 2,000. It adjusts every response to fit.

When the agent needs to take action, it uses skills — modular capabilities that map to your phone's hardware. The SMS skill sends texts. The voice skill uses speech-to-text and text-to-speech. The hardware skill controls the flashlight, IR blaster, and sensors. The scheduler runs tasks on a timer.

No ports are exposed. No cloud server in the loop. Every gateway uses outbound polling — the phone never accepts inbound connections. Your conversations and data stay on your device.

Agent Architecture
💬
9 Communication Gateways
SMS, Twilio (voice + WhatsApp), Voice AI (phone calls), Telegram, Discord, webhook, notification, Screen Agent, Browser Agent
🧠
AI Brain + SecurityEngine (T0-T3)
Claude (primary) → Gemini (fallback). Vision: screenshot analysis via Claude Vision API. SecurityEngine: 4-tier classification, audit trail, rate limits, kill switch
9 Engine Modules
Phone, System, Memory, File, Plugin, Task, Scheduler, Automation, Vision. Plus 8 skills: hardware, media, SMS, system, scheduler, twilio, voice, phone-control
📱
79 Android Permissions
Direct access to camera, all sensors, GPS, Bluetooth, NFC, IR blaster, SMS, phone calls, contacts, calendar, files, biometrics

Ideas to get you started

📞

Voice AI Calls

Call your Twilio number and have a full conversation with AI. Say "create a shopping list" and it writes the file. Say "turn on the flashlight" and it does it. Two-way voice control of your entire phone — new in v8.3.

💬

Smart Auto-Reply

When you're busy, the agent reads your incoming texts and replies intelligently on your behalf. It knows your context, your schedule, and your tone. Not a canned response — a real conversation.

🏠

Home Automation Hub

Use your phone's IR blaster to control TVs and appliances. Send commands via text message. "Turn off the living room TV" — the agent parses it and fires the right IR signal.

📊

Server Monitor

Schedule health checks for your websites and APIs. If something goes down, the agent texts you immediately. It can even attempt auto-recovery by hitting restart endpoints.

📍

Location-Aware Assistant

The agent can read your GPS and respond to questions like "where's the nearest coffee shop?" or log your location at intervals for trip tracking — all processed locally.

📰

Daily Briefing

Schedule a morning summary. The agent checks your calendar, reads the weather, scans your GitHub notifications, and sends you a single digest message before you even open the app.

🛡️

Security Sentinel

Use the camera and sensors as a motion detector. The agent monitors for changes and sends you an alert with a photo if something triggers. No cloud camera subscription needed.

📝

Voice Notepad

Say "hey mobile" and dictate a note, reminder, or idea. The agent transcribes it, processes it with AI to clean up grammar and structure, and saves it to a file you can access later.

🤖

Multi-Platform Bot

Run a single AI that responds across SMS, Telegram, Discord, and WhatsApp simultaneously. Same brain, same personality, every platform — managed from one phone.

AI everywhere on your phone

Three AI interfaces that work across your phone. AI Widget: floating chat overlay on any app. Screen Agent: reads and controls any Android screen via accessibility (click, type, scroll, navigate). Browser Agent: native WebView that auto-injects an AI widget on every web page. Plus Vision — the AI can see your screen.

💬

Floating Overlay

Draggable bubble that expands to a full chat window. Works over any app — reply to AI while browsing, reading, or coding. Tap the bubble to open, drag to reposition, swipe to dismiss.

📷

Camera + Vision

Take photos directly from the widget and get AI analysis in the chat. Point your camera at anything — code on a whiteboard, a bug on screen, a receipt — and the AI describes what it sees.

🎤

Voice Mode

Speech-to-text input and text-to-speech responses. Hands-free operation with a continuous listen-process-speak loop. Skip, pause, or stop at any time.

🔧

Hot Reload Dev

The widget UI is TypeScript compiled with esbuild. During development, it polls for changes every 5 seconds and reloads automatically. WebView + native Kotlin bridge, 17 JS methods, 14KB bundle.

Multi-agent coordination

Give your phone a goal. It decomposes it into tasks, spawns parallel AI agents in separate terminal tabs, and coordinates them through the Agent Bridge — a filesystem-based protocol with task management, lock arbitration, and 2/3 majority consensus voting. Each agent gets a full 200K context window. Claude implements, Gemini reviews, Codex plans.

🐝

Agent Bridge Protocol

mcli-bridge task create "build weather app" — creates a task that any agent can claim. mcli-bridge consensus create triggers a vote. 2/3 majority auto-resolves. Heartbeats, locks, and message queues — all filesystem-based.

💻

Tab Spawning API

mcli-new-tab "command" — shell scripts can programmatically create new terminal sessions. Each agent gets its own isolated tab with full context.

🔀

Git Branch Coordination

Each agent works on its own feature branch. When done, mcli-swarm merge combines all work. File-based status tracking at ~/.mobilecli/swarm/.

🔧

IDE Integration

VS Code and Cursor Agent run via proot-distro Ubuntu. One-tap launch from the app drawer. Full IDE experience on your phone — code-server on localhost.

Connect multiple phones into one system

Turn any MobileCLI phone into a node in a peer-to-peer mesh network. Execute commands on remote devices, transfer files, read hardware sensors across phones, and coordinate AI agents — all over WiFi with SSH key-based authentication. No cloud. No server. Just phones talking to phones.

How Phone Mesh works

mcli-mesh scan pings your local network and probes every IP for MobileCLI's SSH service on port 8022. Discovered peers show up with their hostname and latency. mcli-mesh pair does a bidirectional SSH key exchange — both phones trust each other instantly.

Once paired, you can run any command on the remote phone: mcli-mesh exec peer "termux-battery-status" returns the other phone's battery as JSON. mcli-mesh hw peer photo fires the remote camera. mcli-mesh send peer file.zip transfers files via SCP. mcli-mesh sync peer ~/project uses rsync for full directory synchronization.

Every operation is logged with timestamps and latency. The mesh is fully autonomous — AI agents on one phone can query hardware on another. A phone sitting on your desk becomes a remote sensor, camera, or compute node that any agent can reach.

Mesh Architecture
📱
Phone A (S24 Ultra)
Dev phone — runs Claude, Gemini, Codex. Initiates mesh commands. Paired peers stored in ~/.mobilecli/mesh/peers.json
🌐
WiFi + SSH (Port 8022)
Key-based authentication, no passwords. Bidirectional pairing. All traffic encrypted. Latency tracked per command.
📱
Phone B (S20 Ultra)
Test phone — remote hardware access. Camera, GPS, battery, sensors, SMS, all reachable from Phone A via mcli-mesh hw
📁
13 Commands
scan, peers, pair, unpair, exec, shell, send, fetch, sync, hw (20+ shortcuts), status, log, help

Ideas for the mesh

📷

Remote Camera Network

mcli-mesh hw peer photo fires any paired phone's camera. Set up multiple phones as security cameras, time-lapse rigs, or multi-angle photo captures — all triggered from one terminal.

🔋

Fleet Monitoring

Check battery, WiFi, storage, and sensor data across every phone in your mesh with a single loop. Build a dashboard script that polls all peers every 60 seconds.

📡

Distributed AI Agents

Run Claude on Phone A, Gemini on Phone B. Each agent can reach the other phone's hardware. Coordinate via Agent Bridge. Two brains, two sets of sensors, one mesh.

🔄

Project Sync

mcli-mesh sync peer ~/project uses rsync to keep codebases in sync across devices. Work on your tablet, sync to your phone, deploy from either.

Real work, happening on a phone

This is what a session looks like

You write code. You test it. You deploy it. You manage your repo. The AI helps when you're stuck. All in one terminal, all on your phone.

  • Ask AI to scaffold a new project
  • Edit files with vim or nano
  • Run your dev server locally
  • Commit and push to GitHub
  • Deploy to production with one command
  • Get a notification when the build succeeds
MobileCLI
~ $ claude "create a landing page for my app"
Creating landing page...
✓ Created index.html
✓ Created styles.css
 
~ $ git add . && git commit -m "Add landing page"
[main a3f2b1c] Add landing page
 
~ $ vercel --prod
✓ Deployed to production
→ https://myapp.vercel.app
 
~ $ notification -t "Deployed!" -c "Site is live"

22+ CLIs pre-installed. 1,500+ more available.

Every tool below is pre-configured and ready to use. Plus install anything from the Linux ecosystem — PostgreSQL, Redis, nginx, Go, Ruby, and thousands more.

AI Assistants

Claude — Anthropic
Gemini — Google
Codex — OpenAI
OpenRouter — 100+ models

Deployment

Vercel — Sites & serverless
Firebase — Hosting & backend
Netlify — Sites & edge
Fly.io — Global apps
Heroku — Platform apps

Dev Tools

GitHub CLI — Full Git workflow
Supabase — Database & auth
Godot 4 — Game engine
EAS CLI — React Native
Convex — Realtime backend
VS Code (code-server) — Full IDE
Cursor Agent — AI code editor

Communication & CMS

Telegram — Bots
Discord — Bots
Slack — Apps
Twilio — SMS & voice
Shopify — Storefront
Sanity — CMS
Contentful — Headless CMS
Hugging Face — AI models

Games and engines, made entirely on a phone

Everything below was created using MobileCLI and AI. No PC was involved at any stage.

🕳️
VoidHole v3.0
SDF Raymarching Game Engine
86
FILES
9
SYSTEMS
16
PLAYERS
Complete Game Engine — Godot 4 + GDScript

VoidHole v3.0: AI Game Engine

A complete SDF raymarching game engine. No meshes, no textures, no audio files — everything is math. 9 interconnected systems: chunk streaming, entity system, multiplayer, economy, AI scriptable runtime, procedural audio, and more.

86 source files. 14 autoloads. Built in 18 minutes by Claude Code running inside MobileCLI on a phone.

86
Source Files
9
Systems
6,405
Lines of Code
0
PCs Used
Read the Full Story
Also built on MobileCLI
Play Wasteland v2
Made on Android with CLI + AI + Game Engine

Wasteland v2: Open World

A post-apocalyptic 3D open world with real-time combat, resource gathering, and exploration across 6 biomes. Built with Three.js, playable right here in your browser.

Claude had full control inside the project: designing levels, writing 2,300+ lines of game code, debugging physics, building AI enemies and a day/night cycle. Start to finish, on a phone.

6
Biomes
12
Locations
2,300+
Lines of Code
0
PCs Used
Open Full Screen

This isn't just a terminal.
It's a remarkably capable development environment in your pocket.

Most phones today have hardware comparable to a laptop from a few years ago. Similar CPU cores. Similar RAM. Similar storage. Plus cellular, GPS, cameras, and sensors that laptops typically don't have.

The main difference was software. Phones ran apps for consumers. Laptops ran tools for builders. MobileCLI bridges that gap.

Build your startup's MVP on the train. Fix a production bug from bed. Deploy an update while waiting for coffee. Run an AI agent that manages your communications while you sleep. Connect multiple phones into a mesh and distribute work across devices. Your phone has more potential than you might think. MobileCLI helps unlock it.

Free to try. Pro when you're ready.

7-day free trial. No credit card required. Pro subscription for continued access to all tools and AI assistants.

Pricing details available in the app.

Common questions

Is this safe?
MobileCLI runs locally on your device. AI conversations go directly between your phone and the AI provider (Anthropic, Google, OpenAI). We don't collect your terminal commands, files, or AI conversations. All network traffic uses HTTPS. Your credentials, API keys, and data never leave your phone.
Do I need root?
No. MobileCLI uses 79 Android permissions that provide broad access to hardware, sensors, files, and system features — without rooting your phone. You get root-level capability through legitimate Android APIs.
What phones does it work on?
Any Android phone running Android 7.0 or higher. Works on budget phones too — the terminal is lightweight. An older phone with 2GB of RAM can run it. iOS support is planned for the future.
How is this different from other mobile IDEs?
Most mobile IDEs are toy environments — limited editors with no real build tools. MobileCLI is a full native Linux environment with 22+ pre-configured platform CLIs, 3 AI coding assistants, an autonomous AI agent system, multi-device Phone Mesh, 90+ hardware commands, an automated setup wizard, and self-modification capability. It's not an IDE. It's the entire computer.
Can I really build apps on a phone?
Yes. MobileCLI includes Java 17, Gradle, and Android build tools. You can compile Kotlin, sign APKs, and install them — all on your phone. In fact, MobileCLI itself was built by AI running inside MobileCLI on an Android phone. The app that builds itself.
Do the AI assistants cost extra?
The AI CLIs (Claude, Gemini, Codex) are included in MobileCLI, but each AI provider requires their own API key or subscription. MobileCLI provides the environment; you bring your AI account. You can use your existing Claude Max, ChatGPT Plus, or Gemini subscription, or pay API pricing per use.
What is the AI Agent system?
The AI Agent is an autonomous daemon that runs on your phone. It monitors communication channels (SMS, Twilio, Telegram, Discord), processes messages through AI, and responds using your phone's native capabilities. It supports multiple AI models with automatic fallback, scheduled tasks, voice interaction, and direct hardware control. Think of it as a personal AI assistant that lives on your phone and can actually do things.
Why a command line instead of a regular app?
Three reasons. Security: CLI uses direct encrypted connections with real authentication (OAuth, SSH keys) — no browser vulnerabilities, no cookies to steal. Power: CLI tools have 100% of features that mobile apps intentionally leave out. Extensibility: you can install any Linux package, chain commands together, and automate anything. A GUI can't do that.
What is Phone Mesh?
Phone Mesh lets multiple MobileCLI phones communicate over WiFi using SSH. Run mcli-mesh scan to find peers, mcli-mesh pair to exchange keys, then mcli-mesh exec peer "any command" to run commands on the other phone. You can read remote sensors, take photos on a remote camera, transfer files, and sync entire project directories. All encrypted, no cloud involved.
How do the three AIs work together?
The Agent Bridge protocol (mcli-bridge) provides filesystem-based coordination between Claude, Gemini, and Codex. They can create tasks, claim work, send messages, acquire locks, and vote on decisions via 2/3 majority consensus. Claude typically implements code, Gemini reviews for safety, and Codex plans architecture. The entire protocol is file-based — no servers, no APIs, just JSON files on disk.
What can I install beyond what's included?
Anything that runs on Linux. You have access to 1,500+ system packages (PostgreSQL, Redis, nginx, Go, Ruby, PHP, and more), 2 million+ JavaScript packages via npm, and 500,000+ Python packages via pip. You can even install full Linux distributions (Ubuntu, Debian, Arch). The 100+ pre-installed tools are just the starting point.

Contact

Questions, feedback, partnership inquiries, or just want to show us what you built.

Ready to build something?

Download MobileCLI and find out what your phone can really do.

v10.2.0 adds OACLI Agent System, Screen Agent, Browser Agent, Vision. v10.0.0 is lighter without AI features.

MobileCLI is provided "as is" without warranty. Results vary by device and configuration. AI-generated code may contain errors — you are responsible for reviewing all output. Third-party services (AI providers, cloud platforms) are governed by their own terms. See our Terms of Service for full details.