{"slug": "ai-agent-on-android", "title": "AI Agent on Android", "summary": "A new open-source Android app, RikkaHub Agent, transforms a native LLM chat client into an on-device AI agent with over 80 device tools, including SSH, screen automation, and a Telegram bot. The app allows users to automate tasks via plain language commands, such as scheduling jobs, monitoring notifications, and controlling device functions, all running locally on the phone.", "body_md": "**Your phone, automated.**\n\nA fork of [RikkaHub](https://github.com/rikkahub/rikkahub) that turns the native Android LLM chat client into a real on-device agent: 80+ device tools, AI-authored workflows, scheduled jobs, an in-app browser the AI drives, SSH, screen automation, file manager, music player, voice transcription, downloadable on-device LLMs, and a remote Telegram bot. All opt-in.\n\n[ Website](https://extv.github.io/rikkahub-agent/) ·\n\n[·](https://github.com/ExTV/rikkahub-agent/releases/latest)\n\n**Download**[·](#-features)\n\n**Features**[·](#-quick-start)\n\n**Quick Start**\n\n**Build** Vanilla LLM chat apps can answer questions. They can't open your apps, send your messages, watch your notifications, run scheduled jobs, or SSH into your server. RikkaHub Agent can. Tell it what to do in plain language, walk away, and it runs in the background, on your phone, on your terms.\n\n\"Every weekday at 9am, summarize my unread WhatsApp into one Telegram message.\"\n\n\"If my home server's disk fills up, ping me.\"\n\n\"Watch my notifications. If anything from my boss comes in, forward it to Telegram. Quietly ignore the rest.\"\n\n\"Find the PDF on my phone that mentions 'invoice' and read me the first paragraph.\"\n\n\"Take a screenshot every 30 minutes for the next 4 hours so I can see what I actually did all afternoon.\"\n\n\"Use Termux to build me a webpage listing everything you can do, then open it in my browser.\"\n\n\"When I plug in headphones at home WiFi after 7pm, start my evening playlist.\"\n\n\"Open my router's admin page, sign in with the saved password, and tell me which devices are eating the most bandwidth right now.\"\n\n\"Spin up two researches in parallel: one finds the cheapest one-way flight to Tokyo this month, the other lists hotels in Shibuya under $100. Tell me when both finish.\"\n\nEach of those is a one-line setup. The phone runs them in the background while you live your life.\n\n|\nAsk the AI to tap, swipe, scroll, type, take screenshots, open apps, turn the torch on, change brightness or volume, post a notification, vibrate, share something, or read your battery, WiFi, signal, location, sensors, contacts, and SMS. It can also send an SMS, set the wallpaper, read and write NFC tags, sign and encrypt data with the Android Keystore, reach external storage and SD cards, and zip or unzip archives. Over 80 tools, all built into Android, no extra apps required. Each one stays off until you flip it on. |\nTalk to your assistant from anywhere. Set up a private Telegram bot in a minute, then chat with it like a contact. Send a question, a photo, a PDF, or a voice note. It can run on your behalf while you're at work, while you sleep, or while you're driving. Approval prompts use simple Yes/No buttons in the chat. When the AI needs to ask you something, it pops a tappable multiple-choice question (or takes a free-text reply) right in the chat. A reply too long for one message arrives as a downloadable file instead of getting truncated, and message bursts are paced so Telegram never rate-limits the answer out from under you. |\n|\nThe agent has a real browser built into the app. Watch it open URLs, click through cookie banners, fill in search boxes, scroll, and read the page back to you. Or send it on errands from Telegram. It streams a fresh screenshot to your chat after every step. There's a floating chat pill on the browser screen so you can keep talking to the AI without ever leaving the page. Built-in article extraction and diff-after-action keep the token cost low even on long browse sessions. |\nTasker-style automation, but the AI writes the rules for you. Just describe the trigger and the action: |\n|\nSet tasks to run on a schedule and forget about them. \"Every Monday morning at 8\", \"every two hours\", \"next Friday at 3pm\". The phone keeps everything running through reboots and battery saver. Pick how each task fires: let the AI think at the moment and decide what to do (good for \"watch X and ping me if Y\"), or pre-bake a fixed action that runs without using AI tokens (good for plain reminders). |\nThe AI has its own file manager. Find files, read them, save new ones, copy, move, rename, delete. Same things you'd do in a regular file manager, except you describe what you want and it does it. \"Find every PDF mentioning 'invoice' on my phone\" works in one sentence. System folders that don't belong to you are off-limits, even if you ask. |\n|\nSave your servers once and the AI can SSH into any of them on demand. Run a command, upload a file, pull down a backup, check disk space, tail a log. Pipe input straight into a command or write a remote file in one shot, and launch a long-running server in the background so the call returns its process ID instead of hanging on the connection. Works whether you're on WiFi or cell. Watch your home server from a coffee shop without opening a terminal. |\nIf you have Termux installed, the AI can run real Linux commands on your phone: installing packages, building software, running scripts, or starting a background service that keeps running after the command returns. A dedicated Settings → Termux page lets you tune the command timeout, the per-turn time budget, and other Termux limits when a long install or build needs more room. On top of that, voice notes you send in Telegram get transcribed automatically. Everything runs on your phone, no cloud transcription, no API key, no internet needed. |\n|\nAsk for music and the AI plays it through Android's normal media controls: lock-screen art, headphone keys, the works. Pause, resume, lower the volume for a meeting and bring it back later, all from chat or Telegram. Even after a force-stop the AI can pick up where you left off, same track, same position, via a snapshot fallback. No \"you killed the player so it's gone forever\". Your queue survives. |\nDrop a Markdown skill file into the app and the AI gains a new playbook it'll follow step-by-step: auto-reply to a contact, summarise a notification stack, or run a JavaScript mini-app whose result opens right in the in-app browser. A bundled featured catalog ships with a QR generator, a Wikipedia query box, a piano you can play, an interactive map, and more. Two skills are enabled out of the box: an always-on agent playbook that keeps the assistant proactive and self-improving across sessions, and a converter that adapts OpenClaw skills to run here. Add new skills from a URL, a markdown file you share into the app, or pick from the bundled catalog. |\n|\nFor long tasks the main assistant can dispatch a focused |\nA built-in health checkup for the app. Tap Settings, then Doctor, and it runs a top-to-bottom audit of permissions, background services, database integrity, network, Termux, and diagnostics. Missing something? Tap the auto-fix button next to the row to grant the permission, restart the service, or rebuild the chat search index. The same report runs from Telegram via |\n|\nConnect the assistant to |\nPick which apps the AI is allowed to watch, and it can read, summarize, and forward incoming notifications — the whitelist starts empty, so nothing leaves your phone until you choose. Other apps (Tasker, automation tools, ADB) can also hand the agent a task through the External Automation Intent API, so RikkaHub Agent slots into automation flows you already run. |\n|\nThree layers of protection, in order of strictness:\nPlus: passwords and API keys never make it into log files. The Telegram bot ignores everyone except people you put on its allowlist. Cloud backups skip your saved server credentials and bot token. The notification listener starts with an empty whitelist, so nothing leaves your phone until you pick the apps to forward. |\n\n**Install**: download the latestfrom`*-release.apk`\n\n[Releases](https://github.com/ExTV/rikkahub-agent/releases/latest). Allow install from unknown sources, then open. (One-time note: if you still have an old debug build of RikkaHub Agent installed, uninstall it first — the release build is signed differently and won't upgrade over it.)**Upgrading from a build before** The app id changed to`2.3.1-agent.0`\n\n?`excp.rikkahub`\n\nso the fork installs alongside upstream RikkaHub instead of clashing with it. Android treats the new id as a separate app, so it won't update over an older agent build automatically. To carry your data across: open the old app, make a backup (Settings → Backup), install this release, then restore that backup. Once you've confirmed everything moved over, uninstall the old build.\n\n**Add an LLM provider**: Settings, then Providers, pick one, paste your API key.** OpenRouter**is first-class (auto-detected model capabilities and pricing, provider routing controls), and you can sign in to** Codex**with your ChatGPT account to use your OpenAI plan through OAuth instead of an API key. For fully on-device inference with no key and no network, open the**Local · LiteRT** provider and download a local model (Gemma, Qwen) — it runs on any device and uses the GPU automatically where supported. Multimodal Gemma builds can also read images you attach, decoded on-device where the device's vision encoder is supported (otherwise the model replies from text only). Pixel 8/9/10 users can also flip on the built-in**AICore** card for Gemini Nano.**Turn on what you want**: Settings, then Assistants, tap your assistant, then** Local Tools**, and flip the categories you want enabled.**(Optional) Telegram bot**: message[@BotFather](https://t.me/BotFather)with`/newbot`\n\nto get a bot token, then[@userinfobot](https://t.me/userinfobot)with`/start`\n\nto get your numeric Telegram user id. Then just say to the assistant in chat:*\"Set up the Telegram bot. Token is*It'll handle the rest.`<your token>`\n\n. My user id is`<your id>`\n\n. Set me as the default chat. Enable it.\"\n\nIf you don't turn anything on, the app behaves exactly like vanilla RikkaHub.\n\n| Architecture | arm64 or x86_64 |\n| Android | 8.0+ (API 26), targets API 37 |\n| Storage | ~80 MB app |\n| LLM provider | OpenAI, Google, Anthropic, OpenRouter, Codex (ChatGPT OAuth), Ollama, or any OpenAI-compatible endpoint. OR Gemini Nano via AICore on Pixel 8/9/10+ |\n\nThe interface ships in **English, 简体中文, 繁體中文, 日本語, 한국어, Русский, and العربية**. The app follows your system language automatically and falls back to English for anything not yet translated. Right-to-left languages render correctly in chat and markdown — code blocks stay left-to-right — and Arabic, Persian, and Urdu are available as translator languages.\n\nRequires the [bun](https://bun.sh) JavaScript runtime on PATH. The build chain\nruns `bun install`\n\nand `bun run build`\n\nin `web-ui/`\n\nto produce the in-app web\nUI bundle before packaging the APK.\n\n```\ngit clone https://github.com/ExTV/rikkahub-agent.git\n\ncd rikkahub-agent\n\n./gradlew :app:installDebug   # build + install on a connected device\n```\n\nStands on the shoulders of giants:\n\n| Project | Role |\n|---|---|\n|\n\n[cron-utils](https://github.com/jmrozanec/cron-utils)[whisper.cpp](https://github.com/ggerganov/whisper.cpp)[Termux](https://github.com/termux/termux-app)[JSch (mwiede fork)](https://github.com/mwiede/jsch)[FlorisBoard](https://github.com/florisboard/florisboard)[agent-keyboard](https://github.com/ExTV/agent-keyboard)companionThis fork is unaffiliated with the upstream RikkaHub maintainers. All credit for the underlying chat client, provider abstraction, and UI design goes to the upstream team.", "url": "https://wpnews.pro/news/ai-agent-on-android", "canonical_source": "https://github.com/ExTV/rikkahub-agent", "published_at": "2026-06-19 19:47:51+00:00", "updated_at": "2026-06-19 20:07:29.230403+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "ai-products", "generative-ai"], "entities": ["RikkaHub", "Android", "Telegram", "Termux", "SSH", "NFC", "WhatsApp", "Google"], "alternates": {"html": "https://wpnews.pro/news/ai-agent-on-android", "markdown": "https://wpnews.pro/news/ai-agent-on-android.md", "text": "https://wpnews.pro/news/ai-agent-on-android.txt", "jsonld": "https://wpnews.pro/news/ai-agent-on-android.jsonld"}}