Launch and monitor Cloud Agents
Choose a repository and model, describe the task, and launch a Cloud Agent from your phone. Follow progress, inspect results, and queue additional instructions while work is running.
Kilo Mobile
Kilo Mobile brings Kilo’s AI coding workflow to iPhone, iPad, and Android—launch Cloud Agents, control sessions, and review GitHub pull requests.
What is Kilo Mobile?
Kilo Mobile is a companion app for Kilo’s AI coding workflow on iPhone, iPad, and Android. It lets developers start Cloud Agents from a mobile device, continue supported CLI and VS Code sessions running on a computer, and stay available when an agent needs a response.
The app extends work across Kilo’s mobile, IDE, CLI, and cloud surfaces under one Kilo account. Its mobile workflow covers agent instructions and progress tracking as well as GitHub pull-request review, including diffs, checks, threaded discussion, review submission, and merging.
Mobile coding workflow features
Control desktop sessions
Connect to supported Kilo CLI or VS Code sessions on a computer, send instructions, inspect diffs, and use slash commands on a connected CLI instance.
Review and merge GitHub pull requests
Open GitHub pull requests, inspect checks and syntax-highlighted diffs, leave line comments, submit reviews, reply in threads, and merge from the app.
Receive agent notifications
Configurable push notifications can signal when a session needs input, reaches a milestone, or the account balance is low. The Active now tray keeps live work accessible.
Use voice, attachments, and sharing
Dictate prompts, attach files to a session, or share text, links, and files into Kilo from another app.
Review on iPad
Use side-by-side diffs on iPad for a larger-screen pull-request review experience.
Where Kilo Mobile fits
Start coding work away from a desk
Start a repository task by selecting a model, describing the work, and launching a Cloud Agent. Monitor progress and add follow-up instructions while away from the desktop.
Continue an in-progress desktop session
Pair with a CLI or VS Code session already running on a computer to send additional instructions, review diffs, and keep a long-running task moving during travel or a change of location.
Handle pull-request review on mobile
Open a GitHub pull request from a phone or iPad, check its status and changes, discuss specific lines, submit a review, and merge when the review is complete.
Handle agent requests remotely
Respond promptly when an agent pauses for input or reaches a milestone by using notifications, dictated prompts, attachments, or shared content from another app.
Pros and Cons
Pros
- Launch Cloud Agents and send follow-up instructions without opening a laptop.
- Continue supported Kilo CLI and VS Code sessions from a phone or tablet.
- Review GitHub pull requests with checks, diffs, comments, reviews, thread replies, and merge actions.
- Use push notifications, voice dictation, file attachments, and system sharing to respond from mobile.
- Works across iPhone, iPad, and Android, with side-by-side diffs on iPad.
Cons
- The page specifies support for GitHub pull-request review, but does not establish equivalent mobile pull-request workflows for other repository providers.
- Desktop-session control depends on supported Kilo CLI or VS Code sessions already running on a computer.
- Cloud compute and AI inference are separate usage-based components in Kilo’s broader pricing model, so mobile access does not by itself describe the total cost of running agents.
FAQ
What can I do with Kilo Mobile?
Kilo Mobile lets you launch Cloud Agents, connect to supported Kilo CLI or VS Code sessions on a computer, review GitHub pull requests, and respond when an agent needs input. The app also supports session follow-ups, diffs, slash commands on connected CLI instances, and pull-request actions such as comments, reviews, replies, and merging.
Which devices support Kilo Mobile?
Yes. The product page identifies Kilo Mobile as available for iPhone, iPad, and Android. iPad supports side-by-side diffs for pull-request review.
Can I control a Kilo session running on my computer?
Yes. You can connect to supported Kilo sessions running in the CLI or VS Code on your computer. From the app, you can send instructions, review diffs, and keep long-running work moving; other surfaces remain visible in read-only mode.
Can I review pull requests from the app?
Yes. Kilo Mobile can open GitHub pull requests, show checks and syntax-highlighted diffs, support line comments and review submission, let you reply in threads, and merge the pull request.
Which AI models can I use?
The mobile page says Kilo works with more than 500 AI models and lets users choose a repository and model when launching a Cloud Agent. The pricing page also describes free or local models, provider keys, Kilo Gateway, and Kilo Pass as inference options across Kilo.
Quick Facts
- Category
- Developer tool
- Platforms
- iPhone, iPad, and Android
- Primary workflows
- Cloud Agents, CLI and VS Code session control, GitHub pull-request review
- AI model coverage
- More than 500 supported models
- Account model
- One Kilo account across mobile, IDE, CLI, and cloud
- Product site
- kilo.ai
Kilo Mobile Alternatives
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repos and verifies changes with compilers, debuggers, sanitizers, and tests.
GitBot
GitBot is a local browser workspace for reusable coding bots powered by Claude Code, Codex, or OpenCode, with persistent threads and configurable permissions.
Ghost
Ghost is a terminal-based AI assistant for chatting, code generation, and CLI tasks. Includes free models, supports Linux, macOS, Windows, and is open source.
Vi3ecode
Vi3ecode is a maintained development environment for AI coding agents, keeping project context, terminal, Git, memory, flows and review connected.
Lucid Train
Lucid Train is a local-first AI coding harness that turns repo code into architecture diagrams for coding agents. Desktop app and Rust CLI, local models or API keys.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads in Firecracker micro-VMs with private networking and SDK, CLI, or MCP control.