pocketpal-ai

Project Overview

PocketPal AI is a private AI assistant that runs entirely on your phone. Chat with language models, give them a voice, and let them use tools — all on-device. No account, no cloud, no internet required. Most AI apps are a thin window onto someone else's server — every message you type gets shipped off, logged, and analyzed somewhere you can't see. PocketPal flips that around: the AI lives on your phone, and your conversations never leave it.

Key Features

• On-device chat: Run GGUF language models (Gemma, Qwen, Phi, Llama, and more) fully offline
• Text-to-speech: Give your assistant a voice with on-device neural TTS (Kokoro and other engines), no cloud calls
• Pals: Create personalized assistants with their own model, system prompt, and personality (Assistant and Roleplay types)
• PalsHub: Discover and install community Pals, including premium ones via in-app checkout
• Talents & tools: Let capable Pals call built-in tools (calculator, date/time, rich HTML rendering) inside a tool-use loop
• Hugging Face integration: Search and download GGUF models, including gated ones, directly from the HF Hub with your access token
• Benchmarking: Measure tokens/sec and memory, and optionally compare on the AI Phone Leaderboard
• Hardware acceleration: CPU, GPU (Metal on iOS, OpenCL/Adreno on Android), and NPU (Qualcomm Hexagon) inference paths, with graceful fallback
• Localized: Available in 11 languages, on phones and tablets, including full iPad support

Target Audience

• Privacy-conscious users who don't want conversation data uploaded to the cloud
• Users who need an AI assistant in offline environments (planes, trails, anywhere)
• AI enthusiasts who want to run LLMs locally on their phone
• iOS / Android users

Quick Start

1. Download and install from the App Store (iOS) or Google Play / GitHub Releases (Android)
2. Open the app and download a GGUF model from the built-in model library or Hugging Face
3. Select a model and start chatting offline
4. Configure Pals, voice, and tools as needed

Core Advantages

• Private by default: Every prompt, response, and document stays on your device. Nothing is uploaded or stored on external servers
• Works offline: Download a model once and it just works, with no connection and no account
• Runs on hardware you already own: Real language models, voices, and tools, tuned to make the most of your phone's CPU, GPU, and NPU
• Free and open source: No subscription, no "pro" tier to unlock the AI. MIT-licensed and built in the open

System Requirements

• OS: iOS / iPadOS, Android

Notes

• The only data that ever leaves your device is what you explicitly choose to share: benchmark results (if you opt into the leaderboard) and feedback you submit through the app
• Actual speed and memory usage depend on the model, quantization, and device