# mainframecomputer/fullmoon-ios

chat with private and local large language models

Repository: https://github.com/mainframecomputer/fullmoon-ios
Canonical: https://ross.abutalabs.com/products/fullmoon-ios
Homepage: https://fullmoon.app
Language: Swift
License: MIT
License Family: permissive
Last push: 2025-05-05T13:56:01+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 20, release rhythm 40, longevity 49
- inputs: {"age_days": 694, "days_push": 485, "days_rel": 583, "gap_med": 5, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2267, forks 219 (observed 2026-08-28T04:06:32.779985+00:00)

## What it is
fullmoon is a free, open-source iOS/iPadOS/macOS/visionOS app for chatting with local large language models, built on Apple's MLX Swift framework and optimized for Apple silicon. All chats run fully offline on-device with local history storage and customizable appearance.

## Use cases
- chat with LLMs offline on iPhone
- run private local language models on-device
- chat with Llama 3.2 on iPad
- use DeepSeek-R1 distill models locally on Mac
- keep AI conversations private without internet
- customize a local chatbot's system prompt and theme

## When to choose
- you want private, fully offline LLM chat on Apple devices
- you prefer on-device inference over cloud APIs
- you want a simple native iOS/macOS chat UI for small local models

## When to avoid
- you need large frontier models that exceed on-device memory
- you need Android, Windows, or Linux support
- you want cloud-hosted models or team features

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, chat-interface
- domain: large-language-models, artificial-intelligence, privacy, apple-ecosystem
- platform: -
- tags: local-llm, on-device-inference, mlx, offline-chat, iphone, ipad, visionos, ios, macos, swift, apple-ecosystem

## Member repositories
- mainframecomputer/fullmoon-ios (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:32.779985+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 2026-08-30T02:42:11.688742+00:00, confidence not recorded.
  - readme: https://github.com/mainframecomputer/fullmoon-ios (fetched 2026-08-28T04:06:32.779985+00:00, sha 2dafb3f2c90c)
  - homepage: https://fullmoon.app (fetched 2026-08-29T10:22:29.525496+00:00, sha 1e0b913def21)
- Data as of 2026-08-30T08:39:29.467469+00:00.