Kilo Code vs RelayAI Bridge

Kilo Code App is the mobile companion for Kilo Code, the open source agentic engineering platform. Code, monitor, and steer your agents from your phone, wherever you are. WHAT YOU CAN DO → Code from your phone with Cloud Agents Spin up a Kilo Cloud Agent, give it a task, and review its work from the chat. Full agentic coding, backed by Kilo's managed infrastructure, without opening a laptop. → Connect to your desktop sessions Pair with a Kilo session running in Kilo CLI or VS Code on your computer. Send instructions, review diffs, and keep an eye on long-running tasks while you're away from the desk. → Watch your agents in real time See sessions running outside the app — CLI, IDE, Slack, or cloud — in a live read-only view. Know what your agents are doing, even when you can't intervene. → Review pull requests Paste a GitHub PR link to see checks and full file diffs with syntax highlighting. Leave line-level comments, batch them into a review, approve, reply in threads, and merge. → Work by voice, or from anywhere Dictate prompts instead of typing. Queue follow-ups while an agent is working. Attach any file type. Share links, text, and files into Kilo from any app's share sheet. → Get pinged when an agent needs you Push notifications when a session needs input, hits a milestone, or your balance runs low. An "Active now" tray keeps live sessions at the top with NEEDS INPUT badges. ALSO IN THE APP → Code Reviewer for GitHub, GitLab, and Bitbucket, with a model per repository → Security Agent: posture dashboard, findings to triage, and policy settings → Organizations: members, roles, usage limits, credits, and invoices → Context pressure and session cost in the chat header, with a per-model token breakdown → Sign in with Apple, Google, or a one-time email code → Light, Dark, or System theme WHY KILO → 500+ AI models supported Premium, free, open-source, and open-weight models. Pick the best one for the task, or let Kilo route automatically. → Open source end to end Read the code, audit the behavior, fork it, extend it, run it yourself. No black boxes, no lock-in. → Built by engineers, for engineers We use Kilo to build Kilo. Every feature ships because we needed it ourselves. Credits Top up your Kilo balance with one-off credit packs bought in the app, and spend them on coding agents and model chat. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://kilo.ai/privacy/ Mobile App Privacy Policy (supplementary): https://kilo.ai/privacy/apps

RelayAI lets you manage long-running AI agent work from your iPhone without moving your code out of your local machine. Pair the RelayAI local bridge with your Mac once, then start sessions, send messages, review progress, approve risky actions, and stay attached to work that is still running when you step away from your desk. RelayAI is built for people who already run local agent workflows and want a better remote control surface than constantly SSHing into a laptop from a phone. With RelayAI, you can: - chat with Claude Code and Codex sessions from your iPhone - start and follow long-running local agent sessions remotely - review message history and status updates while a session keeps running on your Mac - approve or deny tool actions when the agent needs confirmation - receive push notifications when a response completes or action is required - pair one or more Macs as local bridges - keep Codex and Claude Code running where your repositories already live RelayAI is built around the local bridge workflow, where Claude Code or Codex stays on your Mac and your iPhone becomes the control surface. You are not limited to passive monitoring. You can continue the conversation, review prior turns, route work to a paired bridge, and manage approvals from the phone while the real runtime keeps working against your local repo. RelayAI is designed around long-running work, not one-off prompts. It keeps your phone and paired bridge aligned around the same session so you can leave your desk without losing control of what the agent is doing.