vtcode 0.121.1

Quick start

Set a provider key and launch VT Code in a project:

export OPENAI_API_KEY="sk-..."
vtcode

Common commands:

vtcode ask "write a Rust factorial function" > factorial.rs
vtcode exec "summarize the current git diff"
vtcode --resume

Features

Installation

macOS and Linux

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

Skip optional search tools:

curl -fsSL https://raw.githubusercontent.com/vinhnx/vtcode/main/scripts/install.sh | bash -s -- --without-search-tools

Windows PowerShell

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

[!NOTE] Windows release artifacts are best-effort and may lag behind macOS/Linux builds.

Package managers

cargo install vtcode
brew install vtcode

# Development tap
brew tap vinhnx/tap
brew install vinhnx/tap/vtcode

[!TIP] Official macOS/Linux release archives include ghostty-vt/ runtime libraries for richer PTY snapshots. Custom installs continue to work with the built-in legacy_vt100 backend.

More details: Installation Guide, Native Installer Guide, Ghostty VT Packaging.

Providers

VT Code supports 20 LLM providers out of the box — from cloud APIs to local inference servers — plus any OpenAI-compatible API through [[custom_providers]].

For detailed setup guides, see Provider Guides.

Provider spotlight: Xiaomi MiMo V2.5 Series

VT Code is happy to be part of the Xiaomi MiMo Orbit Program

Xiaomi's MiMo V2.5 Pro is the default model in VT Code — available as the native MiMo provider and through OpenRouter. It delivers strong performance in agentic capabilities, complex software engineering, and long-horizon tasks with a 1M context window and deep reasoning.

Pricing: Pay-as-you-go · Subscription · Quick Access

Read: Xiaomi MiMo documentation | OpenRouter models.

Atlas Cloud

Atlas Cloud is an LLM provider accessible through VT Code's [[custom_providers]] support — no dedicated runtime provider needed.

[agent]
provider = "atlascloud"
default_model = "deepseek-ai/DeepSeek-V3-0324"

[[custom_providers]]
name = "atlascloud"
display_name = "Atlas Cloud"
base_url = "https://api.atlascloud.ai/v1"
api_key_env = "ATLASCLOUD_API_KEY"
model = "deepseek-ai/DeepSeek-V3-0324"

Other custom OpenAI-compatible providers use the same [[custom_providers]] pattern.

Recommended validated Atlas chat model pool examples for default_model or vtcode ask --model <model-id> include:

• deepseek-ai/DeepSeek-V3-0324
• deepseek-ai/deepseek-r1-0528
• moonshotai/Kimi-K2-Instruct
• Qwen/Qwen3-Coder
• google/gemini-2.5-flash
• openai/gpt-5.2-chat
• anthropic/claude-opus-4.5-20251101
• zai-org/glm-4.7
• minimaxai/minimax-m2.1
• xai/grok-4-0709

Configuration

VT Code reads configuration from vtcode.toml in your project root. The default agent uses the MiMo provider with mimo-v2.5-pro as the default model.

[agent]
provider = "openai"
default_model = "gpt-5.4"

Useful configuration docs:

• Configuration Precedence
• Config Field Reference
• Tool Configuration
• Lifecycle Hooks

Extension points

Skills

VT Code discovers repository, user, admin, and bundled system skills using the open Agent Skills SKILL.md format.

vtcode skills list
vtcode skills info my-skill
vtcode skills create my-skill
vtcode skills validate ./.agents/skills/my-skill

Read: Agent Skills Guide.

MCP

VT Code ships as both an MCP client and server:

• Client: connect to any MCP server for tools like Figma, Playwright, Sentry, and more.
• Server: expose VT Code tools to external agents and editors.

Read: MCP Integration.

Agents and editors

• Zed: native ACP support with project-wide indexing.
• VS Code / Copilot: use the vtcode ask CLI or background agent mode.
• Claude Code: VT Code can operate as a subagent under claude.

Read: Zed ACP Guide, VS Code Guide, Claude Code Guide.

Safety model

VT Code runs a read-restricted shell. Every command passes through a sandbox that can block dangerous operations, log activity, and enforce policy.

Read: Safety Architecture, Security Hardening, Threat Model.

Protocols and exports

Benchmarks

VT Code has a pending submission to vercel/next-evals-oss, the benchmark behind the Next.js AI Agent Evaluations leaderboard.

Development

git clone https://github.com/vinhnx/vtcode.git
cd vtcode
./scripts/run-debug.sh

VT Code uses Rust stable, edition 2024, and MSRV 1.88. The dev profile disables incremental compilation (sccache). Set CARGO_INCREMENTAL=1 to override.

Local checks:

./scripts/check-dev.sh             # fast gate (clippy, fmt, check)
./scripts/check-dev.sh --test      # + unit and integration tests
./scripts/check-dev.sh --workspace # + all workspace crates
./scripts/check-dev.sh --lints     # + additional lints

Running tests:

cargo nextest run                   # parallel runner (preferred)
cargo nextest run -p vtcode-core    # single crate
cargo nextest run test_name         # single test by name

Launching VT Code:

./scripts/run-debug.sh   # debug build + launch
./scripts/run.sh         # release build + launch

Both auto-bootstrap the Ghostty VT runtime. Without it, PTY snapshots fall back to legacy_vt100.

Read: Development Setup, Testing, CI/CD.

Contributing

Contributions are welcome -- typos, docs, bugs, code, ideas. Start with open issues or good first issues. For AI agents, read AGENTS.md first. Humans should also read CONTRIBUTING.md.

Support

VT Code is built in my spare time and shared freely with the community. If it helps you ship code, learn, experiment with agents, or save a few hours, a small donation helps me keep improving it.

You can support ongoing development at buymeacoffee.com/vinhnx. Stars, issues, feedback, and word of mouth also mean a lot.

Star History

If you find VT Code useful, please consider starring the repository. It helps more developers discover the project and gives the community a visible signal that the work is valuable.

License

This repository is licensed under the MIT License.