Cargo (Rust package manager)

<img src="./resources/logo/vt_code_adaptive.svg" alt="vtcode"/>

<a href="./docs/skills/SKILLS_GUIDE.md"><img src="https://img.shields.io/badge/Agent%20Skills-black?style=for-the-badge" alt="Agent Skills"/></a> <a href="./docs/guides/zed-acp.md"><img src="https://img.shields.io/badge/agent%20client%20protocol-black?style=for-the-badge&logo=zedindustries" alt="zed"/></a> <a href="./docs/guides/mcp-integration.md"><img src="https://img.shields.io/badge/model%20context%20protocol-black?style=for-the-badge&logo=modelcontextprotocol" alt="MCP"/></a>

<a href="https://crates.io/crates/vtcode"><img src="https://img.shields.io/crates/v/vtcode?style=flat-square&color=000&label=crates.io" alt="Crates.io Version"/></a> <a href="https://github.com/vinhnx/vtcode/releases"><img src="https://img.shields.io/github/v/release/vinhnx/vtcode?style=flat-square&color=000&label=Release" alt="GitHub Release"/></a>

---

<strong>VT Code</strong> is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management.

<p align="center">
  <img src="./resources/gif/vtcode.gif" alt="VT Code" />
</p>

---

## Installation

**Native Installer (Recommended)** - No dependencies, instant setup:

**macOS & Linux:**

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

**Windows (PowerShell):**

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

**Alternative Installation Methods:**

```bash
# Cargo (Rust package manager)
cargo install vtcode

# Homebrew (macOS/Linux)
brew install vinhnx/tap/vtcode
```

**See [Installation Guide](./docs/installation/) and [Native Installer Guide](./docs/installation/NATIVE_INSTALLERS.md) for more options and troubleshooting.**

## Usage

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

# Launch VT Code
vtcode
```

### AgentSkills Support

VT Code includes comprehensive support for AgentSkills, following the [open Agent Skills standard](http://agentskills.io/). AgentSkills enable VT Code to leverage external capabilities and extend its functionality through a standardized skill system.

Key features of AgentSkills support:

- **Skill Discovery**: VT Code can discover and load skills from multiple locations with precedence handling
- **Standard Compliance**: Fully compliant with the Agent Skills specification for interoperability
- **Multi-Location Support**: Skills can be loaded from local directories, remote repositories, or embedded resources
- **Extensible Ecosystem**: Integrate with the growing ecosystem of Agent Skills for enhanced capabilities

For more information about AgentSkills implementation in VT Code, see [Agent Skills Guide](./docs/skills/SKILLS_GUIDE.md).

### Supported Providers

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

Set the corresponding environment variable for your provider (see [Installation Guide](./docs/installation/#supported-ai-providers) for all options).

### Agent Protocols

VT Code supports multiple agent protocols for integration:

#### Agent Client Protocol (ACP)

VT Code can integrate with code editors like Zed. To configure ACP, refer to the [ACP docs](./docs/guides/zed-acp.md).

#### Agent2Agent (A2A) Protocol

VT Code implements the [Agent2Agent (A2A) Protocol](https://a2a-protocol.org), enabling communication and interoperability between AI agents. The A2A protocol supports:

- **Agent Discovery**: Via Agent Cards at `/.well-known/agent-card.json`
- **Task Lifecycle Management**: States like `submitted`, `working`, `completed`, `failed`
- **Real-time Streaming**: Via Server-Sent Events (SSE)
- **Rich Content Types**: Text, file, and structured data parts
- **Push Notifications**: Webhook-based async updates
- **JSON-RPC 2.0**: Over HTTP(S) for interoperability

For more information about A2A protocol support, see [A2A Protocol Documentation](./docs/a2a/a2a-protocol.md).

#### Anthropic API Compatibility

VT Code provides compatibility with the [Anthropic Messages API](https://docs.anthropic.com/en/api/messages) to help connect existing applications to VT Code, including tools like Claude Code.

The server supports:

- Messages endpoint at `/v1/messages`
- Streaming responses
- Tool calling
- Vision (image) support
- Multi-turn conversations
- System prompts
- All major Anthropic API features

For more information about Anthropic API compatibility, see [Anthropic API Documentation](./docs/a2a/a2a-protocol.md).

#### Open Responses Specification

VT Code conforms to the [Open Responses](https://www.openresponses.org/) specification, an open, vendor-neutral standard for large language model APIs. This enables interoperable LLM workflows across different providers.

Key features of Open Responses conformance:

- **Unif

... (truncated)