Kilo Code vs Talaria Agent Client

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. Subscription Details Kilo App offers three monthly auto-renewable subscription tiers under "Kilo Pass": - Kilo Pass $19 credits — $24.99/month (entry tier) - Kilo Pass $49 credits — $63.99/month (mid tier) - Kilo Pass $199 credits — $259.99/month (high tier) Each tier grants the corresponding dollar amount of AI usage credits each month, used to run coding agents and chat with AI models inside the app. Payment will be charged to your Apple ID account at confirmation of purchase. Subscriptions automatically renew unless auto-renew is turned off at least 24 hours before the end of the current period. Your account will be charged for renewal within 24 hours prior to the end of the current period at the same price as the previous period. You can manage your subscription and turn off auto-renewal at any time by going to your Apple ID Account Settings after purchase. 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

Talaria is a native iPhone client for Hermes Agent — the open-source agent you run on your own computer. It is not a chatbot with a server behind it. It talks to your machine, runs your models, and holds your credentials on your phone. REQUIRES HERMES AGENT You need Hermes Agent running on a computer you control: github.com/NousResearch/hermes-agent Talaria connects to it over your own network. There is no Talaria account and no service in the middle. If you do not run Hermes, this app has nothing to connect to — open it and tap "Look around with sample data" to see how it works first. EVERY CONVERSATION, EVERYWHERE Sessions you started in the CLI, in the desktop app, or through a chat platform all show up in one list, with previews and the branch each was working on. Pick one up on your phone exactly where you left it. WATCH IT WORK Replies stream in as they are written. Every tool run is there to read — the command, the output, the file it touched — instead of a spinner and a summary. Charts and images the agent generates appear inline. YOU STAY IN THE LOOP When the agent is about to do something destructive, it stops and asks. Approvals, clarifying questions, sudo requests and credential prompts arrive on your phone, and nothing runs until you answer. TALK TO IT Hold the microphone and speak. Recognition happens on your phone whenever iOS has the language model installed, and falls back to your gateway's provider when it does not. Choose the engine for each direction in Settings. SCHEDULED TASKS See what your agent is set to do and when, read what happened on past runs, and edit the schedule, the model and the prompt from your phone. SKILLS, TOOLS AND MEMORY Browse installed skills and turn them on or off. See connected MCP servers and the tools they expose. Read the agent's memory. Browse the working directory. WHAT IT COSTS TO RUN Token counts and spend per model, so you can see what a conversation actually cost. CHOOSE THE MODEL PER CONVERSATION Set the model and the thinking level before you send the first message, or change either mid-conversation. Eight thinking levels, from off to ultra. HOW IT CONNECTS Over HTTPS to a gateway with a valid certificate, or with a prompt to inspect and trust a self-signed one — the same way an SSH client asks about a host key. Plain HTTP is allowed only to addresses that cannot leave a private network: Tailscale, your LAN, or localhost over a forwarded port. Credentials live in the iOS keychain. PRIVACY No account. No analytics. No crash reporting. No server operated by us, because there isn't one. The only place your data goes is the gateway you point it at. Talaria is not affiliated with Nous Research.