Install and configure edwardarwin
Install and configure edwardarwin: Emma Darwin: a playful local macOS AI companion with F4 speech, Live2D motion, SQLite memory and desktop MCP tools. Mixed-license source release.
Follow the source instructions for edwardarwin. Read the prerequisites and configuration steps before running an example.
Install on macOS
Tested on Apple Silicon with macOS 27. Native Liquid Glass requires macOS 26 or later; this release does not include an Intel build. Allow several GB for the app, Python dependencies, and models. The Mac app is an unsigned development build, not a notarized App Store release.
-
Install Homebrew if needed, then install dependencies:
brew install uv node ollama -
Download the source, or clone it:
git clone https://github.com/Up-to-code/edwardarwin.git cd edwardarwin -
Obtain Cubism SDK for Web from Live2D’s official download page, review its license, and copy
Core/live2dcubismcore.jsintolive2d-ui/src/renderer/WebSDK/Core/. Cubism Core is proprietary and is intentionally not distributed as a standalone runtime in this source release. -
Prepare the local backend and web interface:
./setup-macos.commandThis installs Python 3.12 dependencies, downloads Supertonic 3 and SenseVoice, pulls
qwen3:1.7binto Ollama, and builds the UI. It does not upload your personal files. -
Download and unzip Emma-Darwin-macOS-arm64.zip from Releases. Move
Emma Darwin.appto~/Applications, open it, and choose the source folder from step 2. If macOS blocks this unsigned build, review it and use macOS’s normal Open Anyway flow in Privacy & Security.To build the Mac app yourself instead, install Xcode Command Line Tools (
xcode-select --install), then run:./install-macos.command -
Use the float icon in the header, or run
./run-desktop-avatar.commandto start floating mode.
Microphone and screen capture require the relevant permissions in System Settings → Privacy & Security. Enable screen access only when you want to use capture or screen-text tools. Chrome needs to be installed for opening links. If another Ollama server is already running, setup uses that server’s existing model directory.
Check the installation
After setup, continue with the first example. If a command fails, compare the runtime version, working directory, and required configuration with the original README before changing dependencies.
Source and help
Source captured: 2026-10-11
