anythingllm-mobile

Product Overview

AnythingLLM Mobile brings the local-first ethos of AnythingLLM to your phone. We believe intelligence should be private, instant, and available on every device you own, with all the context you want it to have.

Mobile devices, even the most cutting edge, are quite limited in models they can run before they overheat or run out of memory, so AnythingLLM Mobile takes a hybrid approach: your phone is the agent harness, and the model can live wherever makes sense for you. Run a small language model (SLM) right on the device, pair over your network with LM Studio, AnythingLLM Desktop, or llama.cpp, or connect to the cloud provider you already use. Wherever the tokens come from, your tools, documents, and chats stay on your device and run with the same care and token efficiency you get across every AnythingLLM product.

Just want private, offline chat? Download an SLM and you're done. Want more, like long-horizon research, document generation, or recurring background jobs? Point the app at on-premise compute or the cloud and keep going. Either way, your data is what makes your AI useful, and it never leaves your phone unless you decide it should.

Basically imagine Openclaw or Heremes agent, but fully on-device first, with all the tools for true utility right out of the box, but no infrastructure to set-up or depend on.

See it in action

Features

Models

• On-device LLM inference - Run GGUF models locally with llama.rn (llama.cpp for React Native). Works with no signal at all.
• On-device vision - Attach images and chat about them using multimodal models, fully offline.
• Hugging Face model browser - Discover, download, and manage models without leaving the app, with a fit badge that tells you whether a model will run well on your phone.
• Tuned to your device - Context windows and capabilities scale to your phone's RAM; prompts are laid out to preserve the KV cache between turns so on-device replies start fast.
• Connect to AnythingLLM - Pair with your desktop or server instance for full workspace and document chat.
• Bring your own provider - Ollama, LM Studio, OpenRouter, Anthropic, OpenAI, or any OpenAI-compatible API, with automatic model discovery and prompt caching where the provider supports it.

Everywhere on your phone

• 🤖 Default Assistant - Make AnythingLLM your phone's default digital assistant and invoke it from any app. A translucent overlay opens over what you're doing so you can talk or type, optionally share a screenshot of the screen with vision models, and save the conversation as a thread. Set it up under Settings › Special tools › Device Assistant.
• 📝 Ask with AnythingLLM - Select text in any app and it appears in the selection toolbar. Polish, shorten, fix grammar or make it formal, or summarize, pull key points, explain and research what you're reading - with the model you chose, not the OEM assistant. Edits are ephemeral; summaries are saved as threads. Switch it off under Settings › Special tools.
• 📤 Share to AnythingLLM - Send photos, documents and links from any app straight into a chat. Links are scraped, documents are parsed, and the empty thread suggests what to do with them.
• ⏰ Scheduled jobs - Ask for a recurring task (a morning news digest, a weekly check-in) and the assistant runs it on schedule, even in the background.
• 🔔 Lock-screen notifications - Get notified when a reply finishes while your phone is locked.

Chat

• 🎙️ Voice input - Tap the mic and talk. Speech-to-text uses your phone's native recognition and keeps up with natural pauses.
• 🧠 Memory - A basic manually managed memory system, globally or per workspace, and recalls it when relevant.
• 🛠️ Built-in tools - Web search, web page reading, summarization, location, time, calendar reading and creation,