Back to directory

Enchanted

An open-source, Ollama-compatible macOS, iOS, and visionOS app for chatting with privately hosted language models such as Llama 2, Mistral, or Vicuna.

Enchanted

Enchanted provides a ChatGPT-style interface across the Apple ecosystem for talking to models the user runs themselves through Ollama, rather than a hosted model, and requires the user to run their own Ollama server to use it. Features include multimodal input, Markdown rendering with tables and code blocks, conversation history stored on-device, custom prompt templates, editing a message or resubmitting it against a different model, a macOS Spotlight-style panel, and full offline use once a model is downloaded and reachable.

When the Ollama server runs on the same machine rather than a shared network address, the documentation describes forwarding it with ngrok so the app on a phone or headset can reach it. The README notes that a project named Jaz is the newer iteration succeeding this one.

It is written in Swift and distributed under the Apache-2.0 license, requiring Ollama v0.1.14 or later.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.