ECLIPSE LOCAL AI - a developer AI chat that runs fully on your computer

Your chats and code never leave your machine: the AI model runs locally through Ollama.

WHAT YOU NEED
  - Python 3.10 or newer (Windows and macOS: https://www.python.org/downloads/ ;
    on Windows tick "Add python.exe to PATH")
  - Internet for the first run, and free disk space for the model:
      about 5 GB on computers with less than 32 GB of memory (qwen2.5-coder:7b)
      about 19 GB on computers with 32 GB or more (qwen3-coder:30b)

HOW TO START
  Windows : double-click  Start-Windows.bat
            (if Windows says it protected your PC: More info, then Run anyway)
  macOS   : double-click  Start-Mac.command
            (the first time: right-click it and choose Open, because it's from the internet)
  Linux   : open a terminal in this folder and run   ./start.sh

The first run installs Ollama, downloads the AI model that fits your computer and sets up
the Python packages. That takes a while. After that, the same file just opens the app.

GOOD TO KNOW
  - "Run code" under a code block runs that code on your computer with your permissions,
    for up to 5 seconds. Read code before you run it.
  - Changes the AI suggests to your files are shown as a diff first, and only written when you accept.
  - Your chats and settings are kept in the .eclipse folder in your home folder.
  - Other models: install any with Ollama (ollama pull <name>) and pick it in Settings.
