VT Code

VT Code is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter. Supports multiple LLM providers with automatic failover and efficient context management.

> Development blog: Lessons from Building VT Code: An Open-Source CLI AI Coding Agent<

---

Installation

macOS & Linux:

curl -fsSL https://raw.githubusercontent.com/vinhnx/vtcode/main/scripts/install.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/vinhnx/vtcode/main/scripts/install.ps1 | iex

Package Managers:

brew install vtcode          # Homebrew
cargo install vtcode         # Cargo
npm install -g @vinhnx/vtcode  # npm

See Installation Guide for more options and troubleshooting.

Usage

# Set your API key
export OPENAI_API_KEY="sk-..."

# Launch VT Code
vtcode

Supported Providers

VT Code works with OpenAI, Anthropic, Google Gemini, xAI, DeepSeek, OpenRouter, Z.AI, Moonshot AI, MiniMax, Ollama (local & cloud), and LM Studio (local).

Set the corresponding environment variable for your provider (see Installation Guide for all options).

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. Key configuration features include:

• Lifecycle Hooks: Execute shell commands in response to agent events - see Lifecycle Hooks Guide
• Tool Policies: Control which tools are allowed, prompted, or denied
• Security Settings: Configure human-in-the-loop approval and workspace boundaries
• Performance Tuning: Adjust context limits, timeouts, and caching behavior

For full configuration options, see Configuration.

---

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, MiniMax, Ollama (local)
• Three-Tier Memory System: Non-destructive conversation memory with working memory, compressed summaries, and persistent session logs - maintains context across long conversations and enables cross-session learning (docs)
• Code Intelligence: Tree-sitter parsers for Rust, Python, JavaScript/TypeScript, Go, Java, Swift
• Semantic Search & RAG: Vector database abstraction (vtcode-vectordb) and document retrieval pipeline (vtcode-rag) for semantic code search and knowledge retrieval
• Smart Tools: Built-in code analysis, file operations, terminal commands, and refactoring
• Editor Integration: Native support for Zed IDE via Agent Client Protocol (ACP)
• Lifecycle Hooks: Execute custom shell commands in response to agent events for context enrichment, policy enforcement, and automation (docs)
• 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

• Installation
  • Native Installers
  • Quick Reference
• Getting started
  • Interactive mode
  • Command line interface
  • Custom prompts
  • Configuration
• AI Provider Setup - Complete guides for configuring different LLM providers:
  • OpenAI, Anthropic, Google Gemini
  • OpenRouter
  • Ollama
  • LM Studio
• Context Engineering
  • Token budget management
  • Dynamic context curation
• Code Intelligence
• Agent Client Protocol (ACP)
• Zed Integration - Agent Client Protocol Integration. VT Code is fully capable ACP agent, works with ACP Clients, for example Zed.
• Lifecycle Hooks - Execute shell commands in response to agent events, enabling context enrichment, policy enforcement, and automation
• Custom Prompts
• Exec Mode
• Development
  • Testing
  • CI/CD
• Architecture
• Security
  • Security Model
  • Security Audit
  • Tool Policies

---

Visual Studio Code Extension

VT Code is available as an VS Code extension.

The original VTCode extension for Visual Studio Code with full semantic code understanding and AI assistance.

VT Code is also compatible with other VS Code-compatible editors:

Compatible with Cursor, Windsurf, and other VS Code-compatible editors through the Open VSX registry.

For installation instructions and download links for other IDEs, visit our IDE Downloads page. For troubleshooting, see the IDE Integration Troubleshooting Guide.

---

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.