VS Code

Install and configure in VS Code

One extension, three inference backends — Apple Intelligence on your Mac, Alibaba Token Plan in the cloud, or Ollama on your own machine (or the team gateway). Same Copilot-style sidebar chat, inline completion, and auto-apply.

View all VS Code extension version history

Choose an inference backend

All three backends share the same sidebar chat, inline completion, explain/refactor commands, and auto-apply. Switch anytime from VS Code settings or the Command Palette.

Backend	Setting value	Best for	Requires
Apple Intelligence	`local-bridge`	On-device inference on Apple Silicon; terminal chat (Codex-style REPL)	macOS menu bar app on `:8765`
Alibaba Token Plan	`alibaba-token-plan`	Org-hosted Qwen, DeepSeek, Kimi, GLM, and more — no local GPU	Token Plan API key from InfoSec
Ollama (self-hosted)	`suherman-ollama`	Local `ollama` or team gateway; coding-focused models with auto routing	Local Ollama on `:11434`, or gateway API key

VS Code Code Intelligence sidebar chat with auto-apply — Sidebar chat

Vibe coding from the activity bar

Open the Code Intelligence panel and auto-apply generated code into workspace files — powered by Apple Intelligence, Alibaba Token Plan, or Ollama, with full workspace context.

Switch backends in one setting

Set Inference Backend to local-bridge, alibaba-token-plan, or suherman-ollama. Configure model picker, auto-apply, workspace file context, and chat profile from VS Code settings.

Officeless Code Intelligence VS Code extension settings — Settings

Step 1 — Install the extension

Download the latest VSIX using the button above.
Open VS Code → Extensions (⇧⌘X) → ⋯ → Install from VSIX….
Select the downloaded .vsix file and reload when prompted.

Backend A

Apple Intelligence (local)

Code stays on your Mac. Requires the macOS menu bar app running on localhost:8765.

Prerequisites

macOS 14+ (Apple Intelligence: macOS 26+)
Install the macOS app and confirm the menu bar bridge is running
Verify: curl http://127.0.0.1:8765/v1/status

Configure in VS Code

Command Palette (⇧⌘P) → Officeless: Use Apple Intelligence
Or set Inference Backend to local-bridge
Set Api Base Url to http://127.0.0.1:8765
Command Palette → Officeless: Check Bridge Status

{
  "officelessCodeIntelligence.inferenceBackend": "local-bridge",
  "officelessCodeIntelligence.apiBaseUrl": "http://127.0.0.1:8765",
  "officelessCodeIntelligence.enableInlineCompletion": true,
  "officelessCodeIntelligence.contextLines": 0,
  "officelessCodeIntelligence.chatProfile": "general",
  "officelessCodeIntelligence.autoApplyCode": true,
  "officelessCodeIntelligence.includeWorkspaceFiles": true
}

Terminal chat (Officeless: Open Terminal Chat) requires this backend. See the Codex integration guide.

Backend B

Alibaba Token Plan (cloud)

Organization-hosted models via Anthropic-compatible API. No macOS app required — works on any machine with VS Code and a Token Plan API key from InfoSec.

Prerequisites

Token Plan API key from your InfoSec team
Endpoint: https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic

Configure in VS Code

Command Palette → Officeless: Use Alibaba Token Plan
Command Palette → Officeless: Configure Token Plan API Key
Pick a model in settings or the chat toolbar (default qwen3.7-plus)
Command Palette → Officeless: Check Token Plan Status

{
  "officelessCodeIntelligence.inferenceBackend": "alibaba-token-plan",
  "officelessCodeIntelligence.tokenPlanBaseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
  "officelessCodeIntelligence.tokenPlanModel": "qwen3.7-plus",
  "officelessCodeIntelligence.enableInlineCompletion": true,
  "officelessCodeIntelligence.contextLines": 0,
  "officelessCodeIntelligence.chatProfile": "general",
  "officelessCodeIntelligence.autoApplyCode": true,
  "officelessCodeIntelligence.includeWorkspaceFiles": true
}

Supported models include qwen3.7-max, qwen3.7-plus, qwen3.6-flash, deepseek-v4-pro, kimi-k2.6, glm-5, MiniMax-M2.5, and more. Switch models from the chat toolbar without restarting.

Backend C

Ollama (self-hosted)

Run coding models on your own hardware with Ollama, or use the team gateway at ai.suherman.net. OpenAI-compatible chat API — no macOS bridge required.

Option 1 — Local Ollama (fully self-hosted)

Install Ollama and pull a coding model, e.g. ollama pull qwen2.5-coder:7b
Confirm Ollama is listening on http://localhost:11434
Command Palette → Officeless: Use ai.suherman.net (Ollama), then set Ollama Ai Base Url to http://localhost:11434 (no API key needed for localhost)

Option 2 — Team gateway (hosted Ollama)

Create an API key at ai.suherman.net/admin
Command Palette → Officeless: Use ai.suherman.net (Ollama)
Command Palette → Officeless: Configure ai.suherman.net API Key

Models & auto routing

Set Ollama Ai Model to auto to route by task complexity (simple → 3B, coding/plan/review → 7B), or pick explicitly: qwen2.5-coder, deepseek-coder, codellama, codegemma, starcoder2, and more. Enable Enable Large Models for 30B on 32 GB+ hosts.

{
  "officelessCodeIntelligence.inferenceBackend": "suherman-ollama",
  "officelessCodeIntelligence.ollamaAiBaseUrl": "http://localhost:11434",
  "officelessCodeIntelligence.ollamaAiModel": "auto",
  "officelessCodeIntelligence.planOllamaUrl": "http://localhost:11434",
  "officelessCodeIntelligence.enableInlineCompletion": true,
  "officelessCodeIntelligence.contextLines": 0,
  "officelessCodeIntelligence.chatProfile": "general",
  "officelessCodeIntelligence.autoApplyCode": true,
  "officelessCodeIntelligence.includeWorkspaceFiles": true
}

For the team gateway, use https://ai.suherman.net as Ollama Ai Base Url instead of localhost.

Switch anytime. All three backends share sidebar chat, inline completion, explain/refactor commands, and auto-apply. Change inferenceBackend in settings or run Officeless: Use Apple Intelligence, Officeless: Use Alibaba Token Plan, or Officeless: Use ai.suherman.net (Ollama) from the Command Palette.

Step 4 — Inline completion & selection commands

Type in any file — ghost-text completions appear (accept with Tab).
Select code → Officeless: Explain Selection or Officeless: Refactor Selection.
Select code → Officeless: Ask About Selection to send it to sidebar chat.

Need guardrails and Officeless MCP? Install the full Officeless Code Intelligence IDE IDE with ten built-in extensions, or sync guardrails into this repo via npm run sync-context. Download branded IDE →

05Extension catalog

VSIX packs for every Officeless coding surface

Install the core agent, AI context hub, MCP explorer, and guardrail modules individually — or use the branded IDE where they ship preloaded.

Standalone VS Code

Code Intelligence

mekari-vas.officeless-code-intelligence

Copilot-style coding chat and inline completion — Apple Intelligence (macOS menu bar app), Claude via Code Intelligence Gateway, Alibaba Cloud Model Studio Token Plan, or ai.suherman.net (Ollama).

Extensions → ⋯ → Install from VSIX… — or use Officeless: Check for Extension Updates when already installed.

Branded IDE + VSIX

Officeless AI Context

mekari-vas.officeless-ai-context

Hub extension — welcome walkthrough, guardrail catalog, connect AI providers, copy Cursor rules.

Built into Code Intelligence IDE; install VSIX on standard VS Code for guardrail hub commands.

Branded IDE + VSIX

Officeless MCP

mekari-vas.officeless-mcp

Mekari IAM OAuth → Officeless MCP gateway — tools explorer and native MCP sync for Copilot Chat.

Command Palette → Officeless: Connect MCP after install.

Branded IDE + VSIX

Guardrails (all modules)

mekari-vas.officeless-guardrails

All Officeless guardrail modules in one extension — global, platform, frontend, design system, prompts, roles, and AI models.

Command Palette → Officeless: Browse All Guardrails — single VSIX for all guardrail modules.

Recommended Marketplace extensions

Optional — install via Extensions view or npm run install:extensions from officeless-code-intelligence.

Extension	Extension ID	Purpose
GitHub Copilot	`github.copilot`	Inline suggestions and chat (sign in with org subscription).Extensions view → search by name, or npm run install:extensions from the repo.
GitHub Copilot Chat	`github.copilot-chat`	Copilot chat panel in VS Code.Extensions view → search by name, or npm run install:extensions from the repo.
Continue	`continue.continue`	BYOK chat and autocomplete — OpenAI, Anthropic, Ollama, and more.Extensions view → search by name, or npm run install:extensions from the repo.
Claude Code	`anthropic.claude-code`	Anthropic Claude assistant for VS Code.Extensions view → search by name, or npm run install:extensions from the repo.
Gemini Code Assist	`google.geminicodeassist`	Google Gemini coding assistant.Extensions view → search by name, or npm run install:extensions from the repo.
Playwright Test	`ms-playwright.playwright`	End-to-end testing for web apps.Extensions view → search by name, or npm run install:extensions from the repo.
ESLint	`dbaeumer.vscode-eslint`	JavaScript and TypeScript linting.Extensions view → search by name, or npm run install:extensions from the repo.
Prettier	`esbenp.prettier-vscode`	Code formatter for JS/TS, JSON, Markdown, and more.Extensions view → search by name, or npm run install:extensions from the repo.
Tailwind CSS IntelliSense	`bradlc.vscode-tailwindcss`	Autocomplete and linting for Tailwind classes.Extensions view → search by name, or npm run install:extensions from the repo.
Code Spell Checker	`streetsidesoftware.code-spell-checker`	Spelling checker for source code and docs.Extensions view → search by name, or npm run install:extensions from the repo.
YAML	`redhat.vscode-yaml`	YAML language support and validation.Extensions view → search by name, or npm run install:extensions from the repo.
REST Client	`humao.rest-client`	Send HTTP requests from `.http` files.Extensions view → search by name, or npm run install:extensions from the repo.

Developer install (optional)

git clone https://bitbucket.org/jojocoders/officeless-code-intelligence.git
cd officeless-code-intelligence
npm run extension:install
# Open extension/ in VS Code and press F5

← Back to home