Enchanted

Enchanted is a chat application for macOS, iOS, and visionOS that connects to private, self-hosted language models via Ollama.

Enchanted is an open-source interface for interacting with privately hosted language models like Llama 2, Mistral, and Vicuna. It functions as a client for an Ollama server, providing a ChatGPT-like experience on Apple devices. The application supports multimodal inputs, including voice prompts and image attachments, and renders markdown content such as tables and code blocks. Users can define custom system prompts, edit messages, and maintain conversation history stored locally on their devices. It is designed for those requiring secure, offline-capable access to their own AI models.

Enchanted at a glance

Best for: Software engineer
Runs on: macOS, iOS, visionOS
Pricing: Free
Released: December 2023
Category: AI chat assistant
Website: github.com/gluonfield/enchanted

Key features

Voice prompts and text-to-speech functionality
Multimodal input support including image attachments
Markdown rendering for tables and code blocks
Customizable system prompts for conversations
Conversation history stored locally on the device
Support for macOS, iOS, and Vision Pro
Spotlight panel access on macOS

Use it for

Interacting with private, self-hosted LLMs
Drafting and testing custom prompt templates
Managing conversation history across Apple devices
Accessing AI models offline

Companions

Tools that articles about Enchanted recommend using with it, each with its job.

Ollama — Built to work with Ollama.
AnythingLLM — Runs fully on-device with no accounts, API keys, or token limits required.
LangChain — Framework for custom agents with memory and tools on local models.
Chroma — Local vector database for embeddings and semantic search.
Cline — Open source, any model, with approval on every step
OpenHands — Runs autonomous agents locally, in the cloud, or inside your VPC with complete control.

Alternatives to Enchanted

LibreChat — Unifies multiple AI models and tools in one customizable, open-source platform.
llmspy.org — Self-host access to 530+ AI models across 24 providers with built-in tools.
HuggingChat UI — It provides a customizable open source chat interface for any OpenAI-compatible backend.
apfel — Runs fully on-device with zero configuration, API keys, or model downloads.
IntelliBar — Connects to multiple AI models and local models without subscription fees.
Sidekick — Chat with local models using your own files and websites offline.
MindMac — A native macOS client supporting multiple AI models with an inline mode and secure keychain storage.
Maid — Run models locally on-device or connect to remote providers securely.
Parlor — Runs fully locally on Apple Silicon and Linux with instant response times.
Open WebUI — Run AI on your own terms with complete data privacy and self-hosting control.
Chat UI — It runs instantly anywhere with a web browser and weighs under 100 KB.
StrictLLM — It keeps your AI workflows secure and reviewable with sandboxed MCP servers and strict tool permissions.

All Enchanted alternatives