# a-ghorbani/pocketpal-ai

An app that brings language models directly to your phone.

Repository: https://github.com/a-ghorbani/pocketpal-ai
Canonical: https://ross.abutalabs.com/products/pocketpal-ai
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-26T14:58:49+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 52
- inputs: {"age_days": 738, "days_push": 7, "days_rel": 8, "gap_med": 4.0, "n_releases_24m": 83}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8067, forks 842 (observed 2026-08-28T04:10:12.431399+00:00)

## What it is
PocketPal AI is an open-source mobile app that runs GGUF language models entirely on-device for private, offline chat. It supports model downloads, text-to-speech, and tool use without any cloud or account.

## Use cases
- chat with llms offline on my phone
- run local language models on android or ios
- private ai assistant without cloud
- download and run gguf models on mobile
- use an ai chatbot with no internet
- keep conversations private on-device

## When to choose
- you want fully private, offline LLM chat on a phone
- you need an AI assistant that works without internet or accounts
- you want a free open-source alternative to cloud chat apps

## When to avoid
- you need frontier-scale model quality that phones cannot run
- you want server-side deployment or multi-user API access
- you need desktop or web-based inference

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, chat-interface, tts, machine-learning
- domain: large-language-models, artificial-intelligence, chatbots, mobile-development, privacy, cross-platform
- platform: cross-platform
- tags: on-device-ai, gguf, offline-llm, react-native, local-inference, private-ai, android, ios, mobile

## Member repositories
- a-ghorbani/pocketpal-ai (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:12.431399+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:31:21.979549+00:00, confidence not recorded.
  - readme: https://github.com/a-ghorbani/pocketpal-ai (fetched 2026-08-28T04:10:12.431399+00:00, sha 426bce12328f)
- Data as of 2026-08-30T08:39:29.467469+00:00.