# gluonfield/enchanted

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

Repository: https://github.com/gluonfield/enchanted
Canonical: https://ross.abutalabs.com/products/enchanted
Language: Swift
License: Apache-2.0
License Family: permissive
Topics: ios, large-language-model, llm, ollama, ollama-app, swift, llama, llama2, mistral
Last push: 2026-07-07T19:34:55+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 91, release rhythm 57, longevity 71
- inputs: {"age_days": 994, "days_push": 57, "days_rel": 79, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5998, forks 426 (observed 2026-08-28T04:09:34.150129+00:00)

## What it is
Enchanted is an open-source iOS/macOS/visionOS chat app that connects to a self-hosted Ollama server to chat with private local language models like Llama 2, Mistral, and Vicuna. It provides a ChatGPT-style interface with multimodal support, prompt templates, and privacy-focused unfiltered completions across Apple devices.

## Use cases
- chat with local llm on iphone
- chatgpt-style app for ollama
- private self-hosted llm chat client for mac
- talk to llama 2 from my phone
- ios app for mistral via ollama
- multimodal chat with local models on vision pro

## When to choose
- you run an Ollama server and want a native Apple-ecosystem chat client
- you want privacy-focused local LLM chat on iPhone, Mac, or Vision Pro
- you need prompt templates and multimodal input with self-hosted models

## When to avoid
- you don't want to host your own Ollama server
- you need a client for OpenAI or other cloud LLM APIs
- you're on Android, Windows, or Linux

## Facets
- artifact type: application
- maturity: active
- function: chatbot, llm-inference, chat-interface
- domain: large-language-models, self-hosted, privacy, apple-ecosystem
- platform: -
- tags: ollama, visionos, llm-client, chatgpt-alternative, local-models, ios, macos, swift

## Member repositories
- gluonfield/enchanted (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.150129+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 2026-08-29T17:49:49.692226+00:00, confidence not recorded.
  - readme: https://github.com/gluonfield/enchanted (fetched 2026-08-28T04:09:34.150129+00:00, sha e5872a17db25)
- Data as of 2026-08-30T08:39:29.467469+00:00.