Officeless Code Intelligence iconOfficeless Code IntelligenceDownload
Apple Intelligence coding bridge for VS Code

Apple Intelligence for VS Code, running locally on your Mac.

Officeless Code Intelligence is a native macOS bridge that exposes Apple Foundation Models through a secure localhost API. Get inline completion in VS Code, or use the terminal chat for Codex-style prompt-only coding — without sending your code to the cloud.

Terminal chatInline completionLocal-only privacyDevOps Central profileVS Code extension
Officeless Code Intelligence app icon

Features

Local AI coding, native on macOS

Apple does not expose Apple Intelligence as a normal remote HTTP API. This bridge keeps the model native on macOS and gives VS Code a simple localhost contract.

Terminal chat (Codex CLI style)

Prompt-only REPL in your terminal — like OpenAI Codex or Gemini CLI. See the Codex integration guide for setup.

Inline completion in VS Code

The extension calls a local HTTP API as you type. Completions stay on your Mac unless you explicitly allow cloud fallback.

Apple Foundation Models

Uses Apple's on-device language model through the Foundation Models framework on macOS 26+, with Private Cloud Compute where available.

Provider abstraction

Automatic routing across Apple Intelligence, Ollama, OpenAI, and Anthropic. One localhost API for every editor integration.

Explain and refactor commands

Select code in VS Code and ask for an explanation or a safe refactor without leaving the editor.

Menu bar control plane

A lightweight macOS agent shows provider status, recent requests, privacy mode, and server health.

Local-only privacy mode

Default mode keeps prompts on-device. Cloud providers are blocked until you opt in to fallback.

Architecture

One local API, many model backends

VS Code talks to a single localhost server. The macOS app converts editor context into Foundation Models prompts and returns completion text to the extension.

├─VS Code
├─Custom Extension
├─http://127.0.0.1:8765/v1/code/complete
├─Officeless Code Intelligence
├─Foundation Models
└─Apple Intelligence

Example request

POST /v1/code/complete
{
  "language": "typescript",
  "filePath": "src/api/users.ts",
  "prefix": "const user = await",
  "suffix": "",
  "instruction": "complete the next line"
}

Chat request

POST /v1/chat
{
  "message": "How do I deploy secret-broker to prod-vas?",
  "profile": "devops",
  "context": "optional pasted code or file content",
  "history": [
    { "role": "user", "content": "..." },
    { "role": "assistant", "content": "..." }
  ]
}

Endpoints

  • /v1/code/complete
  • /v1/code/explain
  • /v1/code/refactor
  • /v1/chat

Privacy

Your code should not leave your machine by surprise

Officeless Code Intelligence is designed for teams that want Apple Intelligence in the editor without routing every keystroke through a remote SaaS API.

Local-only by default

Code context stays on your Mac. Cloud providers are disabled until you change privacy mode.

Optional path redaction

Strip full file paths from prompts before they reach any model backend.

Local request log

Recent requests are stored in the menu bar app for transparency, not uploaded anywhere.

Localhost binding

The bridge listens on 127.0.0.1 only. Nothing is exposed to your network.

Get started

Choose your setup path

Install guides live on dedicated pages — start with the macOS bridge, then add VS Code or Codex-style terminal chat.

macOS app

Download the signed DMG, install the menu bar bridge, and verify localhost :8765.

Download & install →

VS Code

Install the VSIX, configure settings, and use inline completion plus explain/refactor commands.

Install extension →

OpenAI Codex

Codex-style terminal chat powered by Apple Intelligence — prompt-only, local on your Mac.

Set up terminal chat →