An VS Code ChatGPT Copilot Extension

The Most Loved Open-Source ChatGPT Extension for VS Code

ChatGPT Copilot is a powerful and telemetry-free extension for Visual Studio Code, bringing the capabilities of ChatGPT directly into your coding environment.

Features

• 🤖 Supports GPT-4, o1, Claude, Gemini, Ollama, Github and other OpenAI-compatible local models with your API key from OpenAI, Azure OpenAI Service, Google, Anthropic or other providers.
• 💥 Model Context Protocol (MCP) to bring your own tools and DeepClaude (DeepSeek R1 + Claude) mode for best AI responses.
• 📂 Chat with your Files: Add multiple files and images to your chat using @ for seamless collaboration.
• 📃 Streaming Answers: Receive real-time responses to your prompts in the sidebar conversation window.
• 📖 Prompt Manager: Chat with your own prompts (use # to search).
• 🔥 Tool calls via prompt parsing for models that don't support native tool calling.
• 📝 Code Assistance: Create files or fix your code with one click or keyboard shortcuts.
• ➡️ Export Conversations: Export all your conversation history at once in Markdown format.
• 📰 Custom Prompt Prefixes: Customize what you are asking ChatGPT with ad-hoc prompt prefixes.
• 💻 Seamless Code Integration: Copy, insert, or create new files directly from ChatGPT's code suggestions.
• ➕ Editable Prompts: Edit and resend previous prompts.
• 🛡️ Telemetry Free: No usage data is collected.

Recent Release Highlights

• v4.9: Add prompt based tool calls for models that don't support native tool calling.
• v4.8: New LOGO and new models.
• v4.7: Added Model Context Protocol (MCP) integration.
• v4.6: Added prompt manager, DeepClaude mode (DeepSeek + Claude) mode, Github Copilot provider and chat with files.

Installation

• Install the extension from the Visual Studio Marketplace or search ChatGPT Copilot in VScode Extensions and click install.
• Reload Visual Studio Code after installation.

Supported Models & Providers

AI Providers

The extension supports major AI providers with hundreds of models:

Provider	Models	Special Features
OpenAI	GPT-4o, GPT-4, GPT-3.5-turbo, o1, o3, o4-mini	Reasoning models, function calling
Anthropic	Claude Sonnet 4, Claude 3.5 Sonnet, Claude Opus 4	Advanced reasoning, large context
Google	Gemini 2.5 Pro, Gemini 2.0 Flash, Gemini Pro	Search grounding, multimodal
GitHub Copilot	GPT-4o, Claude Sonnet 4, o3-mini, Gemini 2.5 Pro	Built-in VS Code authentication
DeepSeek	DeepSeek R1, DeepSeek Reasoner	Advanced reasoning capabilities
Azure OpenAI	GPT-4o, GPT-4, o1	Enterprise-grade security
Azure AI	Various non-OpenAI models	Microsoft's AI model hub
Ollama	Llama, Qwen, CodeLlama, Mistral	Local model execution
Groq	Llama, Mixtral, Gemma	Ultra-fast inference
Perplexity	Llama, Mistral models	Web-enhanced responses
xAI	Grok models	Real-time information
Mistral	Mistral Large, Codestral	Code-specialized models
Together	Various open-source models	Community models
OpenRouter	200+ models	Access to multiple providers

AI Services

Configure the extension by setting your API keys and preferences in the settings.

Configuration	Description
API Key	Required, get from OpenAI, Azure OpenAI, Anthropic or other AI services
API Base URL	Optional, default to "https://api.openai.com/v1"
Model	Optional, default to "gpt-4o"

Refer to the following sections for more details on configuring various AI services.

OpenAI

Special notes for ChatGPT users: OpenAI API is billed separately from ChatGPT App. You need to add credits to your OpenAI for API usage here. Once you add credits to your API, create a new api key and it should work.

Configuration	Example
API Key	your-api-key
Model	gpt-4o
API Base URL	https://api.openai.com/v1 (Optional)

Ollama

Pull your image first from Ollama library and then setup the base URL and custom model.

Configuration	Example
API Key	ollama (Optional)
Model	custom
Custom Model	qwen2.5
API Base URL	http://localhost:11434/v1/

DeepSeek

Ollama provider:

Configuration	Example
API Key	ollama (Optional)
Model	custom
Custom Model	deepseek-r1
API Base URL	http://localhost:11434/v1/

DeepSeek provider:

Configuration	Example
API Key	your-deepseek-key
Model	deepseek-reasoner
API Base URL	https://api.deepseek.com

SiliconFlow (SiliconCloud) provider:

Configuration	Example
API Key	your-siliconflow-key
Model	custom
Custom Model	deepseek-ai/DeepSeek-R1
API Base URL	https://api.siliconflow.cn/v1

Azure AI Foundry provider:

Configuration	Example
API Key	your-azure-ai-key
Model	DeepSeek-R1
API Base URL	https://[endpoint-name].[region].models.ai.azure.com

Anthropic Claude

Configuration	Example
API Key	your-api-key
Model	claude-3-sonnet-20240229
API Base URL	https://api.anthropic.com/v1 (Optional)

Google Gemini

Configuration	Example
API Key	your-api-key
Model	gemini-2.0-flash-thinking-exp-1219
API Base URL	https://generativelanguage.googleapis.com/v1beta (Optional)

Azure OpenAI

For Azure OpenAI Service, apiBaseUrl should be set to format https://[YOUR-ENDPOINT-NAME].openai.azure.com/openai/deployments/[YOUR-DEPLOYMENT-NAME].

Configuration	Example
API Key	your-api-key
Model	gpt-4o
API Base URL	https://endpoint-name.openai.azure.com/openai/deployments/deployment-name

Github Copilot

Github Copilot is supported with built-in authentication (a popup will ask your permission when using Github Copilot models).

Supported Models:

• OpenAI Models: gpt-3.5-turbo, gpt-4, gpt-4-turbo, gpt-4o, gpt-4o-mini, gpt-4.1, gpt-4.5
• Reasoning Models: o1-ga, o3-mini, o3, o4-mini
• Claude Models: claude-3.5-sonnet, claude-3.7-sonnet, claude-3.7-sonnet-thought, claude-sonnet-4, claude-opus-4
• Gemini Models: gemini-2.0-flash, gemini-2.5-pro

Configuration	Example
Provider	GitHubCopilot
API Key	github
Model	custom
Custom Model	claude-sonnet-4

Github Models

For Github Models, get your Github token from here.

Configuration	Example
API Key	your-github-token
Model	o1
API Base URL	https://models.inference.ai.azure.com

OpenAI compatible Models

To use OpenAI compatible APIs, you need to set a custom model name: set model to "custom" and then specify your custom model name.

Example for groq:

Configuration	Example
API Key	your-groq-key
Model	custom
Custom Model	mixtral-8x7b-32768
API Base URL	https://api.groq.com/openai/v1

DeepClaude (DeepSeek + Claude)

Configuration	Example
API Key	your-api-key
Model	claude-3-sonnet-20240229
API Base URL	https://api.anthropic.com/v1 (Optional)
Reasoning API Key	your-deepseek-api-key
Reasoning Model	deepseek-reasoner (or deepseek-r1 regarding to your provider)
Reasoning API Base URL	https://api.deepseek.com (or your own base URL)

Commands & Keyboard Shortcuts

The extension provides various commands accessible through the Command Palette (Ctrl+Shift+P / Cmd+Shift+P) and keyboard shortcuts.

Context Menu Commands

Context Menu Commands (Right-click on selected code)

Command	Keyboard Shortcut	Description
Generate Code	Ctrl+Shift+A / Cmd+Shift+A	Generate code based on comments or requirements
Add Tests	Ctrl+K Ctrl+Shift+1 / Cmd+K Cmd+Shift+1	Generate unit tests for selected code
Find Problems	Ctrl+K Ctrl+Shift+2 / Cmd+K Cmd+Shift+2	Analyze code for bugs and issues
Optimize	Ctrl+K Ctrl+Shift+3 / Cmd+K Cmd+Shift+3	Optimize and improve selected code
Explain	Ctrl+K Ctrl+Shift+4 / Cmd+K Cmd+Shift+4	Explain how the selected code works
Add Comments	Ctrl+K Ctrl+Shift+5 / Cmd+K Cmd+Shift+5	Add documentation comments to code
Complete Code	Ctrl+K Ctrl+Shift+6 / Cmd+K Cmd+Shift+6	Complete partial or incomplete code
Ad-hoc Prompt	Ctrl+K Ctrl+Shift+7 / Cmd+K Cmd+Shift+7	Use custom prompt with selected code
Custom Prompt 1	Ctrl+K Ctrl+Shift+8 / Cmd+K Cmd+Shift+8	Apply your first custom prompt
Custom Prompt 2	Ctrl+K Ctrl+Shift+9 / Cmd+K Cmd+Shift+9	Apply your second custom prompt

General Commands

General Commands

Command	Description
ChatGPT: Ask anything	Open input box to ask any question
ChatGPT: Reset session	Clear current conversation and start fresh
ChatGPT: Clear conversation	Clear the conversation history
ChatGPT: Export conversation	Export chat history to Markdown file
ChatGPT: Manage Prompts	Open prompt management interface
ChatGPT: Toggle Prompt Manager	Show/hide the prompt manager panel
Add Current File to Chat Context	Add the currently open file to chat context
ChatGPT: Open MCP Servers	Manage Model Context Protocol servers

Prompt Management

Prompt Management

• Use # followed by prompt name to search and apply saved prompts
• Use @ to add files to your conversation context
• Access the Prompt Manager through the sidebar for full prompt management

Model Context Protocol (MCP)

The extension supports the Model Context Protocol (MCP), allowing you to extend AI capabilities with custom tools and integrations.

What is MCP?

What is MCP?

MCP enables AI models to securely connect to external data sources and tools, providing:

• Custom Tools: Integrate your own tools and APIs
• Data Sources: Connect to databases, file systems, APIs, and more
• Secure Execution: Sandboxed tool execution environment
• Multi-Step Workflows: Agent-like behavior with tool chaining

MCP Server Types

The extension supports three types of MCP servers:

Type	Description	Use Case
stdio	Standard input/output communication	Local command-line tools and scripts
sse	Server-Sent Events over HTTP	Web-based tools and APIs
streamable-http	HTTP streaming communication	Real-time data sources

How to configure MCP?

MCP Configuration

1. Access MCP Manager: Use ChatGPT: Open MCP Servers command or click the MCP icon in the sidebar
2. Add MCP Server: Configure your MCP servers with:
   • Name: Unique identifier for the server
   • Type: Choose from stdio, sse, or streamable-http
   • Command/URL: Executable path or HTTP endpoint
   • Arguments: Command-line arguments (for stdio)
   • Environment Variables: Custom environment settings
   • Headers: HTTP headers (for sse/streamable-http)

Example MCP Configurations

File System Access (stdio):

{
  "name": "filesystem",
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/directory"],
  "isEnabled": true
}

Web Search (sse):

{
  "name": "web-search",
  "type": "sse",
  "url": "https://api.example.com/mcp/search",
  "headers": {"Authorization": "Bearer your-token"},
  "isEnabled": true
}

Agent Mode

Agent Mode

When MCP servers are enabled, the extension operates in Agent Mode:

• Max Steps: Configure up to 15 tool execution steps
• Tool Chaining: Automatic multi-step workflows
• Error Handling: Robust error recovery and retry logic
• Progress Tracking: Real-time tool execution feedback

Configurations

Full list of configuration options

Core Configuration

Setting	Default	Description
chatgpt.gpt3.provider	Auto	AI Provider: Auto, OpenAI, Azure, AzureAI, Anthropic, GitHubCopilot, Google, Mistral, xAI, Together, DeepSeek, Groq, Perplexity, OpenRouter, Ollama
chatgpt.gpt3.apiKey		API key for your chosen provider
chatgpt.gpt3.apiBaseUrl	https://api.openai.com/v1	API base URL for your provider
chatgpt.gpt3.model	gpt-4o	Model to use for conversations
chatgpt.gpt3.customModel		Custom model name when using custom model option
chatgpt.gpt3.organization		Organization ID (OpenAI only)

Model Parameters

Setting	Default	Description
chatgpt.gpt3.maxTokens	0 (unlimited)	Maximum tokens to generate in completion
chatgpt.gpt3.temperature	1	Sampling temperature (0-2). Higher = more creative
chatgpt.gpt3.top_p	1	Nucleus sampling parameter (0-1)
chatgpt.systemPrompt		System prompt for the AI assistant

DeepClaude (Reasoning + Chat) Configuration

Setting	Default	Description
chatgpt.gpt3.reasoning.provider	Auto	Provider for reasoning model (Auto, OpenAI, Azure, AzureAI, Google, DeepSeek, Groq, OpenRouter, Ollama)
chatgpt.gpt3.reasoning.apiKey		API key for reasoning model
chatgpt.gpt3.reasoning.apiBaseUrl	https://api.openai.com/v1	API base URL for reasoning model
chatgpt.gpt3.reasoning.model		Model to use for reasoning (e.g., deepseek-reasoner, o1)
chatgpt.gpt3.reasoning.organization		Organization ID for reasoning model (OpenAI only)

Agent & MCP Configuration

Setting	Default	Description
chatgpt.gpt3.maxSteps	15	Maximum steps for agent mode when using MCP servers

Feature Toggles

Setting	Default	Description
chatgpt.gpt3.generateCode-enabled	true	Enable code generation context menu
chatgpt.gpt3.searchGrounding.enabled	false	Enable search grounding (Gemini models only)

Prompt Prefixes & Context Menu

Setting	Default	Description
chatgpt.promptPrefix.addTests	Implement tests for the following code	Prompt for generating unit tests
chatgpt.promptPrefix.addTests-enabled	true	Enable "Add Tests" context menu item
chatgpt.promptPrefix.findProblems	Find problems with the following code	Prompt for finding bugs and issues
chatgpt.promptPrefix.findProblems-enabled	true	Enable "Find Problems" context menu item
chatgpt.promptPrefix.optimize	Optimize the following code	Prompt for code optimization
chatgpt.promptPrefix.optimize-enabled	true	Enable "Optimize" context menu item
chatgpt.promptPrefix.explain	Explain the following code	Prompt for code explanation
chatgpt.promptPrefix.explain-enabled	true	Enable "Explain" context menu item
chatgpt.promptPrefix.addComments	Add comments for the following code	Prompt for adding documentation
chatgpt.promptPrefix.addComments-enabled	true	Enable "Add Comments" context menu item
chatgpt.promptPrefix.completeCode	Complete the following code	Prompt for code completion
chatgpt.promptPrefix.completeCode-enabled	true	Enable "Complete Code" context menu item
chatgpt.promptPrefix.adhoc-enabled	true	Enable "Ad-hoc Prompt" context menu item
chatgpt.promptPrefix.customPrompt1		Your first custom prompt template
chatgpt.promptPrefix.customPrompt1-enabled	false	Enable first custom prompt in context menu
chatgpt.promptPrefix.customPrompt2		Your second custom prompt template
chatgpt.promptPrefix.customPrompt2-enabled	false	Enable second custom prompt in context menu

User Interface

Setting	Default	Description
chatgpt.response.showNotification	false	Show notification when AI responds
chatgpt.response.autoScroll	true	Auto-scroll to bottom when new content is added

How to install locally

Build and install locally

We highly recommend installing the extension directly from the VS Code Marketplace for the easiest setup and automatic updates. However, for advanced users, building and installing locally is also an option.

• Install vsce if you don't have it on your machine (The Visual Studio Code Extension Manager)
  • npm install --global vsce
• Run vsce package
• Follow the instructions and install manually.

npm run build
npm run package
code --uninstall-extension feiskyer.chatgpt-copilot
code --install-extension chatgpt-copilot-*.vsix

Acknowledgement

Acknowledgements

Inspired by gencay/vscode-chatgpt project and made effortlessly accessible thanks to the intuitive client provided by the Vercel AI Toolkit, this extension continues the open-source legacy, bringing seamless and robust AI functionalities directly into the editor with telemetry free.

License

This project is released under ISC License - See LICENSE for details. Copyright notice and the respective permission notices must appear in all copies.