Please check the build logs for more information.
See Builds for ideas on how to fix a failed build, or Metadata for how to configure docs.rs builds.
If you believe this is docs.rs' fault, open an issue.
Quickstart
Installing and running VT Code
Install globally with your preferred package manager. If you use Cargo:
cargo install vtcode
Alternatively, if you use Homebrew:
brew install vinhnx/tap/vtcode
Or if you prefer NPM:
npm install -g vtcode
Then simply run vtcode to get started:
vtcode
Using VT Code with your preferred provider
Set your API key environment variable and run VT Code:
# Set your API key
# Launch VT Code
VT Code Extension for Visual Studio Code
For installation instructions and download links for other IDEs, visit our IDE Downloads page. For troubleshooting, see the IDE Integration Troubleshooting Guide.
Available providers
VT Code supports multiple providers including OpenAI, Anthropic, xAI, DeepSeek, Gemini, Z.AI, Moonshot AI, OpenRouter, and Ollama (local).
Set your preferred API key environment variable:
# OpenAI
# Anthropic
# Google Gemini
# xAI
# DeepSeek
# Z.AI
# Moonshot AI
# OpenRouter
Agent Client Protocol (ACP)
VT Code can integrate with code editors like Zed. To configure ACP, refer to the ACP docs.
Configuration
VT Code supports a rich set of configuration options, with preferences stored in vtcode.toml. For full configuration options, see Configuration.
IDE Integration
VTCode is available as an extension or plugin for the most popular code editors. Download for your favorite IDE to get started with AI-powered coding assistance:
Visual Studio Code
The original VTCode extension for Visual Studio Code with full semantic code understanding and AI assistance.
Winsurf
Coming soon to the Winsurf marketplace. Check back for updates on availability.
Cursor
Coming soon to the Cursor extensions marketplace. Check back for updates on availability.
For installation instructions and additional information, visit our IDE Downloads page.
Key Features
- Security First: Multi-layered security model with execution policy, sandbox integration, and argument injection protection
- Multi-Provider AI: OpenAI, Anthropic, xAI, DeepSeek, Gemini, Z.AI, Moonshot AI, OpenRouter, Ollama (local)
- Code Intelligence: Tree-sitter parsers for Rust, Python, JavaScript/TypeScript, Go, Java, Swift
- Smart Tools: Built-in code analysis, file operations, terminal commands, and refactoring
- Editor Integration: Native support for Zed IDE via Agent Client Protocol (ACP)
- Semantic Search: AST-based search capabilities with ast-grep integration
- Context Management: Advanced token budget tracking and context curation
- TUI Interface: Rich terminal user interface with real-time streaming
Security & Safety
VT Code implements a defense-in-depth security model to protect against prompt injection and argument injection attacks:
- Execution Policy: Command allowlist with per-command argument validation
- Workspace Isolation: All operations confined to workspace boundaries
- Sandbox Integration: Optional Anthropic sandbox runtime for network commands
- Human-in-the-Loop: Configurable approval system for sensitive operations
- Audit Trail: Comprehensive logging of all command executions
See Security Model for details.
Docs & Examples
- Getting started
- Context Engineering
- Code Intelligence
- Agent Client Protocol (ACP)
- Zed Integration
- Custom Prompts
- Exec Mode
- Development
- Architecture
- Security
Support VT Code Development
I build VT Code in my free time as a passion project to research and explore how coding agents work in practice. If you find VT Code useful, please consider supporting my work with a coffee via BuyMeACoffee:
Your support means the world to me, thank you!
License
This repository is licensed under the MIT License.
