aether

KO | EN

gitlite — search

#typescript #ai-agents #ai #dsh-plugin #deepseek-harness #open-source #claude-code #codex #cli #developer-tools #react #windows

★ 51 Open GitHub ↗

Supercharge your GitHub Copilot with multiple AI providers

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Aether

### **Supercharge your GitHub Copilot with 20+ AI providers**

[![Version](https://img.shields.io/visual-studio-marketplace/v/OEvortex.aether-ai?style=for-the-badge&logo=visual-studio-code&logoColor=white&label=Version&color=007ACC)](https://marketplace.visualstudio.com/items?itemName=OEvortex.aether-ai)
[![Downloads](https://img.shields.io/visual-studio-marketplace/d/OEvortex.aether-ai?style=for-the-badge&logo=visual-studio-code&logoColor=white&label=Downloads&color=28A745)](https://marketplace.visualstudio.com/items?itemName=OEvortex.aether-ai)
[![Rating](https://img.shields.io/visual-studio-marketplace/r/OEvortex.aether-ai?style=for-the-badge&logo=visual-studio-code&logoColor=white&label=Rating&color=FFC107)](https://marketplace.visualstudio.com/items?itemName=OEvortex.aether-ai)

[![License](https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge)](https://raw.githubusercontent.com/OEvortex/aether/main/LICENSE)
[![VS Code](https://img.shields.io/badge/VS%20Code-1.104.0+-007ACC.svg?style=for-the-badge&logo=visual-studio-code&logoColor=white)](https://code.visualstudio.com/)
[![Node.js](https://img.shields.io/badge/Node.js-20.0+-339933.svg?style=for-the-badge&logo=node.js&logoColor=white)](https://nodejs.org/)

<br/>

[Install](#installation) · [Quick Start](#quick-start) · [Features](#key-features) · [Providers](#supported-providers)

</div>

---

## Overview

A powerful VS Code extension that provides model support for **GitHub Copilot Chat**, seamlessly integrating **20+ AI providers** including ZhipuAI, MiniMax, MoonshotAI, DeepSeek, Codex (OpenAI), Chutes, OpenCode, Blackbox, Vercel AI, Cline, and custom OpenAI/Anthropic compatible models.

> [!NOTE]
> Aether CLI has been moved to a separate package (`@oevortex/aether`). The CLI is no longer bundled with this extension.

### 🌉 MCP Tool Bridge (New in v0.4.3!)

Aether now includes an **MCP (Model Context Protocol) Bridge** that exposes VS Code Language Model tools to external AI clients:

- **What it does**: Exposes `vscode.lm.tools` to MCP clients like Claude Code, Claude Desktop, Cursor, and Windsurf
- **Auto-Start**: Enabled by default (`aether.mcpBridge.http.enabled`)
- **Port**: Runs on `http://localhost:59684` (configurable via `aether.mcpBridge.http.port`)
- **Features**:
  - Activity Bar panel with tool management (checkboxes to expose/hide tools)
  - Tools grouped by extension with exposure controls
  - HTTP MCP Server using StreamableHTTP transport
  - Dynamic tool discovery with configurable polling
  - Rich tooltips with metadata and input schemas
  - Status bar integration showing server status and tool count

**Quick Start:**
1. Launch Extension Development Host (`F5`)
2. Find **Aether MCP Bridge** in the Activity Bar
3. Click to view and manage tools
4. Run "Aether: Copy MCP Config to Clipboard"
5. Paste into your MCP client config (e.g., `.mcp.json`)

**Example MCP Client Config:**
```json
{
  "mcpServers": {
    "aether-mcp-bridge": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://localhost:59684/mcp", "--allow-http"]
    }
  }
}
```

---

## Supported Providers

</div>

---

## Key Features

### 🔄 Multi-Account Management

> [!TIP]
> 
> Manage multiple accounts per provider with ease

- Add **unlimited accounts** for each AI provider
- Quick switch between accounts with `Ctrl+Shift+Q` / `Cmd+Shift+Q`
- Visual account status in the status bar
- Secure credential storage using VS Code Secret Storage

---

### ⚖️ Load Balancing & Auto-Switching

> [!TIP]
> 
> Automatic load distribution across accounts

- Auto-switch when hitting rate limits or quota exhaustion
- Intelligent retry with exponential backoff strategy
- Real-time quota monitoring and usage statistics
- Seamless failover without interrupting your workflow

---

### 🔐 OAuth Authentication

> [!TIP]
> 
> Secure login for supported providers

---

### 🌐 Web Search Integration

> [!TIP]
> 
> Real-time information retrieval

**Example usage in Copilot Chat:**
```
@workspace #zhipuWebSearch What are the latest features in TypeScript 5.5?
```

---

### ✨ Advanced Code Completion

> [!TIP]
> 
> Smart code completion features

**Enable in Settings:**
```json
{
    "chp.fimCompletion.enabled": true,
    "chp.nesCompletion.enabled": true
}
```

---

## Installation

<details>
<summary><b>📦 From VS Code Marketplace (Recommended)</b></summary>

1. Open **VS Code**
2. Go to Extensions (`Ctrl+Shift+X` / `Cmd+Shift+X`)
3. Search for **"Aether"**
4. Click **Install**

Or visit the Marketplace page directly: [Aether on Visual Studio Marketplace](https://marketplace.visualstudio.com/items?itemName=OEvortex.aether-ai)

</details>

1. Download the `.vsix` file from [Releases](https://github.com/OEvortex/aether/releases)
2. In VS Code, press `Ctrl+Shift+P` / `Cmd+Shift+P`
3. Type **"Extensions: Install from VSIX..."**
4. Select the downloaded file

</details>

<details>
<summary><b>🔨 Build from Source</b></summary>

```bash
# Clone the repository
git clone https://github.com/OEvortex/aether.git
cd aether

# Install dependencies
npm install

# Build the extension
npm run compile

# Package as .vsix
npm run package

# Install the packaged extension
code --install-extension aether-*.vsix
```

</details>

---

## Quick Start

### Step 1: Configure Your Provider

### Step 2: Select Your Model

1. Open GitHub Copilot Chat
2. Click the model dropdown
3. Select a model from your configured provider (e.g., `⦿ ZhipuAI > glm-4.5`)

### Step 3: Configure Multiple Accounts (Optional)

```
Cmd+Shift+P → "Aether: Settings"
→ Select a provider
→ Add accounts with API keys
```

### Step 4: Enable Load Balancing

```
Cmd+Shift+P → "Aether: Settings"
→ Select a provider
→ Toggle "Load Balance" for automatic account switching
```

---

## Detailed Guide: Managing Providers

### How to Configure Providers

Follow these simple steps to add and manage providers using the Settings page:

#### **Step 1: Open Settings**

Press `Cmd+Shift+P` (macOS) or `Ctrl+Shift+P` (Windows/Linux) and type:

```
Aether: Settings
```

#### **Step 2: Select Your Provider**

Click on the provider you want to configure (e.g., ZhipuAI, MiniMax, MoonshotAI, etc.)

#### **Step 3: Add Account Credentials**

Enter your API key and configure provider settings:

- **API Key**: Your provider's API key
- **Base URL**: Custom API endpoint (optional)
- **Additional Settings**: Provider-specific settings exposed by the extension manifest, such as endpoint, SDK mode, and other provider options

#### **Step 4: Enable Load Balancing (Optional)**

Toggle the **"Load Balance"** switch to enable automatic account switching when rate limits are hit.

### Provider Management Features

- **Add Multiple Accounts**: Add multiple API keys per provider for load balancing
- **Edit Settings**: Click the edit icon to modify provider details and provider-specific settings
- **Delete Account**: Remove accounts you no longer need
- **Switch Account**: Use `Ctrl+Shift+Q` / `Cmd+Shift+Q` for quick switching
- **Load Balance**: Automatically distribute requests across accounts
- **Quota Tracking**: Monitor usage and remaining quota in real-time

---

## Configuration Reference

### Global Settings

### Provider-Specific Settings

#### ZhipuAI

#### MiniMax

### Completion Settings

#### FIM (Fill In the Middle)

#### NES (Next Edit Suggestions)

---

## Available Models

### ZhipuAI (GLM Coding Plan)

| Model | Input | Output | Features |
| :---- | :------ | :----- | :------- |
| GLM-4.5 | 98K | 32K | Tool Calling |
| GLM-4.5-air | 98K | 32K | Tool Calling |
| GLM-4.6 | 229K | 32K | Tool Calling |
| GLM-4.7 | 229K | 32K | Tool Calling |
| GLM-5 | 229K | 32K | Tool Calling |
| GLM-4.7-Flash | 229K | 32K | **Free** |

### MiniMax

| Model | Input | Output | Features |
| :---- | :------ | :----- | :------- |
| MiniMax-M2.5 | 172K | 32K | Thinking, Tool Calling |
| MiniMax-M2.5-highspeed | 172K | 32K | ~100 TPS, Thinking |
| MiniMax-M2.1 | 172K | 32K | Thinking, Tool Calling |

### MoonshotAI (Kimi)

| Model | Input | Output | Features |
| :---- | :------ | :----- | :------- |
| Kimi For Coding | 224K | 32K | Tool Calling |
| Kimi-K2-Thinking | 224K | 32K | Thinking, Agentic |
| Kimi-K2-Thinking-Turbo | 224K | 32K | Thinking, Fast |
| Kimi-K2-0905-Preview | 224K | 32K | Agentic Coding |

### DeepSeek

| Model | Input | Output | Features |
| :---- | :------ | :----- | :------- |
| DeepSeek-V3.2 | 128K | 16K | Tool Calling |
| DeepSeek-V3.2 Reasoner | 128K | 16K | Thinking, Tool Calling |

### Codex (OpenAI)

| Model | Input | Output | Features |
| :---- | :------ | :----- | :------- |
| GPT-5.2 Codex | 344K | 65K | Image Input, Tool Calling |
| GPT-5.3 Codex | 344K | 65K | Image Input, Tool Calling |
| GPT-5.3 Codex (Low) | 344K | 65K | Low Reasoning |
| GPT-5.3 Codex (Medium) | 344K | 65K | Medium Reasoning |
| GPT-5.3 Codex (High) | 344K | 65K | High Reasoning |

---

## Keybindings

---

## Commands Reference

### Provider Configuration

### OAuth Authentication

### Account Management

### Utilities

---

## Custom Models (Compatible Provider)

Add your own OpenAI or Anthropic compatible models:

1. Run `Aether: Compatible Provider Settings`
2. Click "Add Model"
3. Configure your model:

```json
{
    "id": "my-custom-model",
    "name": "My Custom Model",
    "baseUrl": "https://api.example.com/v1",
    "apiKey": "your-api-key",
    "model": "model-name",
    "maxInputTokens": 128000,
    "maxOutputTokens": 8192,
    "sdkMode": "openai",
    "capabilities": {
        "toolCalling": true,
        "imageInput": false
    }
}
```

---

## Requirements

| Requirement | Version |
| :---------- | :------ |
| VS Code | `>= 1.104.0` |
| Node.js | `>= 20.0.0` |
| npm | `>= 9.0.0` |
| GitHub Copilot Chat | Required (extension dependency) |

---

## Development

### Build & Test

```bash
# Install dependencies
npm install

# Build in development mode
npm run compile:dev

# Build for production
npm run compile

# Watch mode
npm run watch

# Run linting
npm run lint

# Format code
npm run format

# Package extension
npm run package
```

### Project Structure

```
copilot-helper/
├── src/
│   ├── extension.ts          # Entry point
│   ├── accounts/             # Multi-account management
│   ├── copilot/              # Core Copilot integration
│   ├── providers/            # AI provider implementations
│   │   ├── providerRegistry.ts  # Provider registry
│   │   ├── zhipu/            # ZhipuAI provider
│   │   ├── minimax/          # MiniMax provider
│   │   ├── moonshot/         # MoonshotAI provider
│   │   ├── codex/            # OpenAI Codex
│   │   └── ...               # Other providers
│   ├── tools/                # Web search tools
│   ├── types/                # TypeScript definitions
│   ├── ui/                   # Settings pages
│   └── utils/                # Shared utilities
├── dist/                     # Compiled output
├── package.json              # Extension manifest
└── tsconfig.json             # TypeScript config
```

---

## Credits

Special thanks to these amazing projects:

| [<img src="https://github.com/Pimzino.png" width="80" style="border-radius: 50%"/><br/>**LLMux**](https://github.com/Pimzino/LLMux) | [<img src="https://github.com/VicBilibily.png" width="80" style="border-radius: 50%"/><br/>**GCMP**](https://github.com/VicBilibily/GCMP) |
| :---------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------: |

</div>

---

## 🤝 Support & Contact

### Get in Touch

Have questions or suggestions? Reach out on Telegram:

[![Telegram](https://img.shields.io/badge/Telegram-@OEvortex-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white)](https://t.me/OEvortex)

</div>

---

## License

This project is licensed under the **MIT License** - see the [LICENSE](LICENSE) file for details.

---

### Made with ❤️ for the developer community

**[⬆ Back to Top](#copilot-)**

</div>

aether

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README