llm4free
LLM4Free — All-in-one Python toolkit for web search, AI interaction (40+ free providers), digital utilities, and more. Formerly WebScout.
- 383
- Python
- Apache-2.0
- 3 wk ago
Supercharge your GitHub Copilot with multiple AI providers
Repo OEvortex/aether, read from GitHub 13 h ago. OEvortex has not joined Take My Repo.
OEvortex/aether is a public repo on GitHub by OEvortex. Supercharge your GitHub Copilot with multiple AI providers. It declares the MIT license on GitHub. It is written mainly in TypeScript, has 51 stars and last changed on 2026-07-17. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-22.
In the maintainer's words. Shown from GitHub; Take My Repo does not keep a copy.
Install · Quick Start · Features · Providers
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.
Aether now includes an MCP (Model Context Protocol) Bridge that exposes VS Code Language Model tools to external AI clients:
vscode.lm.tools to MCP clients like Claude Code, Claude Desktop, Cursor, and Windsurfaether.mcpBridge.http.enabled)http://localhost:59684 (configurable via aether.mcpBridge.http.port)Quick Start:
F5).mcp.json)Example MCP Client Config:
{
"mcpServers": {
"aether-mcp-bridge": {
"command": "npx",
"args": ["-y", "mcp-remote", "http://localhost:59684/mcp", "--allow-http"]
}
}
}
| Provider | Description | Key Models | Highlights |
|---|---|---|---|
| Codex | OpenAI Codex | GPT-5.2 Codex, GPT-5.3 Codex | 400k context Image Input OAuth Reasoning Modes |
| ZhipuAI | GLM Coding Plan | GLM-4.5, GLM-4.6, GLM-4.7, GLM-5, GLM-4.7-Flash | 256K context Web Search MCP SDK Free Tier |
| MiniMax | Coding Plan | MiniMax-M2.5, MiniMax-M2.1 | 205K context Web Search Thinking Mode |
| MoonshotAI | Kimi For Coding | Kimi-K2-Thinking, Kimi-K2-0905-Preview | 256K context Agentic Coding Thinking Mode |
| DeepSeek | DeepSeek AI | DeepSeek-V3.2, DeepSeek-V3.2 Reasoner | 128K context GPT-5 Level Reasoning |
| Chutes | Chutes AI | Various models | Global Request Limit |
| OpenCode | OpenCode AI | Claude 4.5, GPT-5 | Multi-model Access |
| Blackbox | Blackbox AI | kimi-k2.5, blackbox-base-2 | Official API API Key Required |
| Vercel AI | Vercel AI Gateway | Dynamic language models | Dynamic Models Vision Tags Context Metadata |
| Cline | Cline API | Dynamic provider/model IDs | Dynamic Models OpenAI SDK Authenticated Discovery |
| DeepInfra | DeepInfra | OpenAI-compatible models | LLM & Image Models |
| Kilo AI | Kilo AI | Dynamic model fetching | High Performance |
| Zenmux | Zenmux AI | Dynamic model fetching | OpenAI-compatible |
| Lightning AI | Lightning AI | Various models | Dynamic Models |
| Hugging Face | Hugging Face | Various models | Router Integration |
| Mistral AI | Mistral AI | Mistral models | OpenAI-compatible |
| NVIDIA NIM | NVIDIA NIM | NVIDIA models | 40 RPM Throttle Model Discovery |
| Ollama Cloud | Ollama | Local & Cloud models | OpenAI-compatible |
| Qwen CLI | Qwen Code CLI | Qwen models | OAuth via CLI |
| Compatible | Custom API | User-defined models | OpenAI/Anthropic Compatible |
[!TIP]
Manage multiple accounts per provider with ease
Ctrl+Shift+Q / Cmd+Shift+Q[!TIP]
Automatic load distribution across accounts
[!TIP]
Secure login for supported providers
| Provider | Auth Method | Command |
|---|---|---|
| Codex | OpenAI OAuth | Aether: Codex Login |
| Qwen CLI | Alibaba OAuth | qwen auth login (CLI) |
[!TIP]
Real-time information retrieval
| Tool | Provider | Description |
|---|---|---|
#zhipuWebSearch |
ZhipuAI | Multi-engine search (Sogou, Quark, Standard) |
#minimaxWebSearch |
MiniMax | Coding Plan web search |
Example usage in Copilot Chat:
@workspace #zhipuWebSearch What are the latest features in TypeScript 5.5?
[!TIP]
Smart code completion features
| Feature | Description | Default |
|---|---|---|
| FIM (Fill In the Middle) | Intelligent code completion based on context | Disabled |
| NES (Next Edit Suggestions) | Predictive editing suggestions | Disabled |
Enable in Settings:
{
"chp.fimCompletion.enabled": true,
"chp.nesCompletion.enabled": true
}
Keybindings:
| Action | Windows/Linux | macOS |
|---|---|---|
| Trigger inline suggestion | Alt+/ |
Alt+/ |
| Toggle NES manual mode | Shift+Alt+/ |
Shift+Alt+/ |
Ctrl+Shift+X / Cmd+Shift+X)Or visit the Marketplace page directly: Aether on Visual Studio Marketplace
.vsix file from ReleasesCtrl+Shift+P / Cmd+Shift+P# 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
| Provider | Command |
|---|---|
| Codex (OpenAI) | Cmd+Shift+P → Aether: Codex Login |
| ZhipuAI | Cmd+Shift+P → Aether: ZhipuAI Configuration Wizard |
| MiniMax | Cmd+Shift+P → Aether: MiniMax Configuration Wizard |
| MoonshotAI | Cmd+Shift+P → Aether: MoonshotAI Configuration Wizard |
| DeepSeek | Cmd+Shift+P → Aether: Configure DeepSeek |
| Chutes | Cmd+Shift+P → Aether: Configure Chutes |
| Zenmux | Cmd+Shift+P → Aether: Configure Zenmux |
| OpenCode | Cmd+Shift+P → Aether: Configure OpenCode |
| Blackbox | Cmd+Shift+P → Aether: Configure Blackbox |
| Vercel AI | Cmd+Shift+P → Aether: Configure Vercel AI |
| Cline | Cmd+Shift+P → Aether: Configure Cline |
| Hugging Face | Cmd+Shift+P → Aether: Configure Hugging Face |
| Kilo AI | Cmd+Shift+P → Aether: Configure Kilo AI |
| Lightning AI | Cmd+Shift+P → Aether: Lightning AI Configuration Wizard |
| DeepInfra | Cmd+Shift+P → Aether: Configure DeepInfra |
| NVIDIA NIM | Cmd+Shift+P → Aether: Configure NVIDIA NIM |
| Mistral AI | Cmd+Shift+P → Aether: Configure Mistral AI |
| Ollama Cloud | Cmd+Shift+P → Aether: Configure Ollama Cloud |
| Custom Models | Cmd+Shift+P → Aether: Compatible Provider Settings |
⦿ ZhipuAI > glm-4.5)Cmd+Shift+P → "Aether: Settings"
→ Select a provider
→ Add accounts with API keys
Cmd+Shift+P → "Aether: Settings"
→ Select a provider
→ Toggle "Load Balance" for automatic account switching
Follow these simple steps to add and manage providers using the Settings page:
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) and type:
Aether: Settings
Click on the provider you want to configure (e.g., ZhipuAI, MiniMax, MoonshotAI, etc.)
Enter your API key and configure provider settings:
Toggle the "Load Balance" switch to enable automatic account switching when rate limits are hit.
Ctrl+Shift+Q / Cmd+Shift+Q for quick switching| Setting | Type | Default | Description |
|---|---|---|---|
chp.temperature |
number | 0.1 |
Controls output randomness (0-2) |
chp.topP |
number | 1 |
Controls output diversity (0-1) |
chp.maxTokens |
number | 8192 |
Maximum output tokens (32-256000) |
chp.rememberLastModel |
boolean | true |
Remember last used model |
| Setting | Type | Default | Description |
|---|---|---|---|
chp.zhipu.search.enableMCP |
boolean | true |
Enable MCP SDK mode for web search |
chp.zhipu.endpoint |
string | "open.bigmodel.cn" |
API endpoint (open.bigmodel.cn or api.z.ai) |
chp.zhipu.plan |
string | "coding" |
Plan type (coding or normal) |
chp.zhipu.thinking |
string | "auto" |
Thinking mode (enabled, disabled, auto) |
chp.zhipu.clearThinking |
boolean | true |
Clear thinking context between turns |
| Setting | Type | Default | Description |
|---|---|---|---|
chp.minimax.endpoint |
string | "minimaxi.com" |
API endpoint (minimaxi.com or minimax.io) |
| Setting | Type | Default | Description |
|---|---|---|---|
chp.fimCompletion.enabled |
boolean | false |
Enable FIM completion |
chp.fimCompletion.debounceMs |
number | 500 |
Debounce delay (50-1000ms) |
chp.fimCompletion.timeoutMs |
number | 5000 |
Request timeout (1000-30000ms) |
| Setting | Type | Default | Description |
|---|---|---|---|
chp.nesCompletion.enabled |
boolean | false |
Enable NES completion |
chp.nesCompletion.manualOnly |
boolean | false |
Only trigger manually (Alt+/) |
chp.nesCompletion.debounceMs |
number | 500 |
Debounce delay (50-1000ms) |
chp.nesCompletion.timeoutMs |
number | 5000 |
Request timeout (1000-30000ms) |
| 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 |
| 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 |
| 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 |
| Model | Input | Output | Features |
|---|---|---|---|
| DeepSeek-V3.2 | 128K | 16K | Tool Calling |
| DeepSeek-V3.2 Reasoner | 128K | 16K | Thinking, Tool Calling |
| 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 |
| Action | Windows/Linux | macOS |
|---|---|---|
| Trigger inline suggestion | Alt+/ |
Alt+/ |
| Toggle NES manual mode | Shift+Alt+/ |
Shift+Alt+/ |
| Attach selection to Copilot | Ctrl+Shift+A |
Cmd+Shift+A |
| Insert handle reference | Ctrl+Shift+H |
Cmd+Shift+H |
| Insert handle (full path) | Ctrl+Alt+Shift+H |
Cmd+Alt+Shift+H |
| Quick switch account | Ctrl+Shift+Q |
Cmd+Shift+Q |
| Command | Description |
|---|---|
Aether: Configure ZhipuAI |
Set ZhipuAI API key |
Aether: ZhipuAI Configuration Wizard |
Full ZhipuAI setup with MCP mode |
Aether: Configure MiniMax |
Set MiniMax API key |
Aether: MiniMax Configuration Wizard |
Full MiniMax setup |
Aether: Configure MoonshotAI |
Set MoonshotAI API key |
Aether: MoonshotAI Configuration Wizard |
Full MoonshotAI setup |
Aether: Configure DeepSeek |
Set DeepSeek API key |
Aether: Configure Chutes |
Set Chutes API key |
Aether: Configure Zenmux |
Set Zenmux API key |
Aether: Configure OpenCode |
Set OpenCode API key |
Aether: Configure Blackbox |
Set Blackbox API key |
Aether: Configure Vercel AI |
Set Vercel AI API key |
Aether: Configure Cline |
Set Cline API key |
Aether: Configure Hugging Face |
Set Hugging Face API key |
Aether: Configure Kilo AI |
Set Kilo AI API key |
Aether: Lightning AI Configuration Wizard |
Full Lightning AI setup |
Aether: Configure DeepInfra |
Set DeepInfra API key |
Aether: Configure NVIDIA NIM |
Set NVIDIA NIM API key |
Aether: Configure Mistral AI |
Set Mistral AI API key |
Aether: Configure Ollama Cloud |
Set Ollama Cloud API key |
Aether: Compatible Provider Settings |
Configure custom models |
| Command | Description |
|---|---|
Aether: Codex Login |
Login to OpenAI Codex |
Aether: Codex Logout |
Logout from Codex |
| Command | Description |
|---|---|
Aether: Add Account |
Add a new account |
Aether: Switch Account |
Switch to another account |
Aether: Quick Switch Account |
Quick switch with Ctrl+Shift+Q |
Aether: Remove Account |
Remove an account |
Aether: View All Accounts |
List all configured accounts |
| Command | Description |
|---|---|
Aether: Toggle NES Manual Trigger Mode |
Toggle NES manual mode |
Aether: Attach Selection to Copilot Chat |
Attach selected code to chat |
Aether: Insert Handle Reference |
Insert #file:filename:L1-L100 |
Aether: Insert Handle Reference with Full Path |
Insert #handle:path/to/file:L1-L100 |
Aether: Open Aether Settings |
Open settings page |
Add your own OpenAI or Anthropic compatible models:
Aether: Compatible Provider Settings{
"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
}
}
| Requirement | Version |
|---|---|
| VS Code | >= 1.104.0 |
| Node.js | >= 20.0.0 |
| npm | >= 9.0.0 |
| GitHub Copilot Chat | Required (extension dependency) |
# 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
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
Have questions or suggestions? Reach out on Telegram:
This project is licensed under the MIT License - see the LICENSE file for details.
OEvortex/aether is a public repo on GitHub by OEvortex. Supercharge your GitHub Copilot with multiple AI providers.
It declares the MIT license on GitHub.
Its maker tagged it for macOS, Windows and Linux, or as Docker or cross-platform. That is declared by the maker; Take My Repo has not tested it.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-07-17. GitHub counts 2 open issues and pull requests. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
LLM4Free — All-in-one Python toolkit for web search, AI interaction (40+ free providers), digital utilities, and more. Formerly WebScout.
A powerful Model Context Protocol (MCP) server for web search and URL content extraction using DuckDuckGo.
unofficial API designed to interact with Google's Gemini
Minimalist coding agent harness with a Textual TUI and headless CLI. <1k-token system prompt, 18+ LLM providers, AGENTS.md + skills context, session tree, prompt/auto permissions.
This page is also available as structured data, with the same sources and dates.
/api/v1/resources/gh/OEvortex/aetherTake My Repo has not tested this on your machine. Requirements come from the project's own documentation.