PocketMind

PocketMind

A private, on-device AI chatbot — your conversations never leave your phone.

PocketMind feature graphic

About

PocketMind is an AI chatbot that runs a local language model directly on your phone, so inference happens entirely on-device and your conversations never leave it. It supports two inference backends — GGUF (llama.cpp) and MediaPipe (.task) — and ships with a built-in model catalog: open-license models download in-app with a single tap, while gated models are guided through the official Hugging Face license flow. You can keep several models on hand and switch quickly, organize work across multiple persistent chat sessions with search and time grouping, and act on individual messages (copy, regenerate, delete). It works fully offline — the network is used only to download models you choose. The App is free and ad-supported, with an optional in-app purchase to remove ads.

Features

  • On-device AI chat — no cloud inference, works offline
  • Two inference backends: GGUF (llama.cpp) and MediaPipe (.task)
  • Built-in model catalog with one-tap in-app download for open-license models
  • Import your own models, keep several on hand, and switch quickly
  • Multiple persistent chat sessions with search and time grouping
  • Message actions: copy, regenerate, and delete
  • One-tap generation presets — Precise, Balanced, and Creative
  • Markdown rendering with code syntax highlighting
  • Material You design with light and dark themes
  • English and Korean interface
  • Your conversations never leave the device
  • Ad-free option via in-app purchase