Skip to content

Repository files navigation

Ontology

A minimalist, local coding IDE for software engineers. Clean file explorer, Monaco editor, integrated terminal, and AI agent — bring your own model.

Ontology

Ontology IDE — agent writing and running Python in your project

New to the codebase? Start with CODEBASE.md — architecture map, agent flow, and file guide.

Features

  • File Explorer — Browse, open, create files and folders
  • Code Editor — Monaco editor with syntax highlighting, tabs, Ctrl+S save
  • Terminal — Integrated shell (PowerShell on Windows, bash on macOS/Linux)
  • AI Chat — Streaming chat with context from your open file
  • BYOM (Bring Your Own Model) — Connect any API:
    • Ollama — Local models (Llama, Mistral, etc.)
    • DeepSeek — DeepSeek API
    • OpenAI — GPT models
    • Custom — Any OpenAI-compatible endpoint

Quick Start

# Install dependencies
npm install

# Run in development
npm start

# Build for production
npm run build

AI Setup

Ollama (Local — Recommended)

  1. Install Ollama
  2. Pull a model: ollama pull llama3.2
  3. In Ontology → Settings → select Ollama
  4. Click Test ConnectionSave

DeepSeek

  1. Get an API key from DeepSeek
  2. Settings → select DeepSeek
  3. Paste your API key → Test → Save

OpenAI / Custom

Settings → select provider → enter API key, base URL, and model name.

Keyboard Shortcuts

Shortcut Action
Ctrl+O Open folder
Ctrl+S Save current file
Enter Send chat message
Shift+Enter New line in chat

Tech Stack

  • Electron + React + TypeScript + Vite
  • Monaco Editor
  • xterm.js + node-pty
  • Tailwind CSS
  • Zustand

License

MIT

About

Ontology, IDE.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages