Enchanted

An iOS/macOS app for conversing with private self-hosted language models

CommonProductProgrammingswiftios

Enchanted is an open-source, Ollama-compatible macOS/iOS/visionOS app that allows users to converse with private self-hosted language models such as Llama 2, Mistral, and Vicuna. It essentially serves as an interface for connecting to a private model, akin to a ChatGPT application. Enchanted aims to provide a product that delivers an unfiltered, secure, private, and multi-modal experience across all devices in the iOS ecosystem (macOS, iOS, Watch, Vision Pro).

Use custom prompt templates anywhere
Supports Markdown for elegant display of tables/lists/code blocks
Supports voice cues and image attachments
Supports editing message content or submitting messages with different models
Supports quick access via macOS Spotlight dashboard
Supports fully offline operation
Supports text-to-speech (reading) functionality
Supports setting system prompts for each conversation

Enchanted is designed for users who wish to have private conversations with self-hosted language models
including researchers
developers
and general users. It offers a secure and private communication environment
supporting multi-modal interaction for greater flexibility in using language models.

Researchers use Enchanted to conduct academic research with self-hosted Llama 2 models.
Developers utilize Enchanted's Markdown support feature to write technical documents.
Ordinary users have daily conversations with the Vicuna model through Enchanted to obtain information and advice.

1. Download the Enchanted app from the App Store.
2. Choose the appropriate setup method based on whether you have access to a public Ollama server.
3. If running a public access Ollama server
specify the server endpoint directly in the app settings.
4. If running Ollama on a local computer

Visit

Enchanted Visit Over Time

Monthly Visits

515580771

Bounce Rate

37.20%

Page per Visit

5.8

Visit Duration

00:06:42

Enchanted Visit Trend

Enchanted Visit Geography

Enchanted Traffic Sources

Enchanted Alternatives

Lingma SWE-GPT — An open-source large language model specifically designed for software improvement.

Programming•Open Source•Artificial Intelligence

Editor Usage — Monitor and manage your Cursor editor usage.

Productivity•Monitoring•Management

OuteTTS-0.1-350M — A text-to-speech synthesis model that operates through a pure language model.

Productivity•Text-to-speech•Voice synthesis

318

MobileLLM-1B — A sub-billion parameter language model developed by Meta, suitable for device-side applications.

Programming•Language Model•Transformer

MobileLLM-600M — An efficient and optimized 600M parameter language model designed for device applications.

Programming•Language Model•Transformer

MobileLLM-350M — An efficiently optimized language model with sub-billion parameters, specifically designed for device-side applications.

Programming•Language Model•Transformer

MobileLLM-125M — An efficient, optimized small language model designed for device-side applications.

Programming•Language Model•Device-side Applications

MobileLLM — Optimized small language model suitable for mobile devices

Productivity•Language Model•Mobile Devices

HOVER — Multi-functional neural full-body controller for humanoid robots

Programming•humanoid robot•neural networks

SimpleQA — A benchmark test for measuring the ability of language models to answer factual questions.

Others•Benchmark•Language Model

AudioLM — High-quality audio generation framework

Others•Audio Generation•Language Model

138

stable-diffusion-3.5-large-turbo — High-performance text-to-image generation model.

Image•Text-to-image•Generation model

414

stable-diffusion-3.5-large — High-performance text-to-image generation model

Image•Image Generation•Text-to-Image

246

Easydict — A simple and easy-to-use translation dictionary application for macOS

Productivity•Translation•Dictionary

IBM Granite 3.0 Models — IBM Granite 3.0 Models, high-performance AI language models

Programming•Machine Learning•Natural Language Processing

Spirit LM — Multimodal language model that integrates text and speech

Productivity•Multimodal•Language Model

Zamba2-7B — High-performance small language model

Productivity•Language Model•Natural Language Processing

126

rag-chatbot — A chatbot that can interact with multiple PDF files locally.

Programming•chatbot•question-answering

108

o1 in Medicine — Preliminary Research of AI in Medicine

Education•Artificial Intelligence•Medicine

o1 — Create o1-style reasoning chains using Groq, OpenAI, or Ollama.

Programming•Groq•OpenAI

WebLLM — High-performance in-browser language model inference engine.

Productivity•Browser•Language Model

AMD-Llama-135m — A high-performance language model trained by AMD

Programming•Language model•Text generation

SFR-Judge — An intelligent evaluation tool that accelerates model assessment and fine-tuning.

Productivity•Artificial Intelligence•Evaluation Tool

Llama 3.2 — Open-source AI model that can be fine-tuned, distilled, and deployed.

Productivity•Machine Learning•Open Source

174

Best AI Websites & Tools

Enchanted

Enchanted Visit Over Time

Enchanted Visit Trend

Enchanted Visit Geography

Enchanted Traffic Sources

Enchanted Alternatives

Chital — Chat application for the Ollama model on macOS

Surfed — Safari History and Bookmark Manager

CLoT — Discover the creative and humorous potential of LLM

GptBoard — The only application integrating AI on macOS/iOS

WriteMage — Integrate AI into your macOS/iOS devices

Lingma SWE-GPT — An open-source large language model specifically designed for software improvement.

Editor Usage — Monitor and manage your Cursor editor usage.

OuteTTS-0.1-350M — A text-to-speech synthesis model that operates through a pure language model.

MobileLLM-1B — A sub-billion parameter language model developed by Meta, suitable for device-side applications.

MobileLLM-600M — An efficient and optimized 600M parameter language model designed for device applications.

MobileLLM-350M — An efficiently optimized language model with sub-billion parameters, specifically designed for device-side applications.

MobileLLM-125M — An efficient, optimized small language model designed for device-side applications.

MobileLLM — Optimized small language model suitable for mobile devices

HOVER — Multi-functional neural full-body controller for humanoid robots

SimpleQA — A benchmark test for measuring the ability of language models to answer factual questions.

AudioLM — High-quality audio generation framework

stable-diffusion-3.5-large-turbo — High-performance text-to-image generation model.

stable-diffusion-3.5-large — High-performance text-to-image generation model

Easydict — A simple and easy-to-use translation dictionary application for macOS

IBM Granite 3.0 Models — IBM Granite 3.0 Models, high-performance AI language models

Spirit LM — Multimodal language model that integrates text and speech

Zamba2-7B — High-performance small language model

rag-chatbot — A chatbot that can interact with multiple PDF files locally.

o1 in Medicine — Preliminary Research of AI in Medicine

o1 — Create o1-style reasoning chains using Groq, OpenAI, or Ollama.

WebLLM — High-performance in-browser language model inference engine.

AMD-Llama-135m — A high-performance language model trained by AMD

SFR-Judge — An intelligent evaluation tool that accelerates model assessment and fine-tuning.

Llama 3.2 — Open-source AI model that can be fine-tuned, distilled, and deployed.