VTCode

Contents

• [New: VT Code WebMCP application](#new-vt-code-webmcp-application)
• [Overview](#overview)
• [Quick start](#quick-start)
• [Documentation](#documentation)
• [Providers and models](#providers-and-models)
• [Local inference](#local-inference-experimental)
• [Development](#development)
• [Contributing](#contributing)
• [Support](#support)
• [License](#license)

> New here? Start with [Installation](./docs/installation/README.md), then > [Getting Started](./docs/user-guide/getting-started.md).

Overview

Secure, open, universal.

VT Code is an open-source Rust terminal coding agent for interactive and long-running autonomous workflows. It combines a responsive TUI, safe terminal tools, multi-provider LLM support, open protocols, and extensible Skills in one tool, so you can move from a question to a reviewed change without leaving your terminal.

> Project status: Active development. > Local inference and some automation workflows are experimental, and > interfaces and configuration may change between releases.

New: VT Code WebMCP application

The WebMCP browser bridge is a first-class, opt-in VT Code integration. The maintained browser app is published at two origins:

| Deployment | URL | Browser origin | Use it for | | --- | --- | --- | --- | | ChatGPT Site | | https://vtcode.vinhnx.chatgpt.site | Hosted WebMCP demonstration | | GitHub Pages | | https://vinhnx.github.io | Static fallback and WebMCP reference client |

The app derives the exact pairing origin from the page currently open, so pair the active VT Code session with /webmcp pair https://vtcode.vinhnx.chatgpt.site for the ChatGPT Site or /webmcp pair https://vinhnx.github.io for GitHub Pages. See the [WebMCP user guide](./docs/user-guide/webmcp.md), [development guide](./docs/development/webmcp.md), [deployment reference](./docs/reference/webmcp.md), [WebMCP app guide](./apps/webmcp/GUIDE.md), [WebMCP app README](./apps/webmcp/README.md), and [WebMCP crate documentation](./crates/codegen/vtcode-webmcp/README.md) for setup, integration, and implementation details.

Runtime and coding

• Agent runtime: interactive TUI, slash commands, streaming, ask/exec CLI, session resume, review workflows, and the authenticated WebMCP browser bridge
• Coding tools: safe file operations, ripgrep search, ast-grep symbol maps, fuzzy discovery, code intelligence, project indexing, and terminal execution

Extensibility and providers

• Extensibility: Agent Skills, MCP client/server, Agent Plugins, lifecycle hooks, subagents, custom providers, and ACP
• Model providers: 30 built-in providers, custom OpenAI-compatible endpoints, and local inference via Ollama, LM Studio, and llama.cpp (managed with /local)

Safety and protocols

• Safety: restricted shell sandbox, tool guardrails, subprocess isolation, audit logging, per-workspace approval before lifecycle hooks defined in workspace configuration (vtcode.toml, .vtcode, or agent-spec files) can run shell commands, and terminal-owned WebMCP pairing/write boundaries
• Provider governance: providers_whitelist restricts which LLM providers VT Code can access, preventing accidental data leakage to unapproved endpoints
• Protocols: Open Responses, Agent2Agent (A2A), ATIF, and Anthropic Messages API

Automation and planning

• Loop engineering: worktree isolation for parallel agents, propose/verify sub-agent separation, durable loop state, and cost guardrails
• Planning workflow: iterate on a build plan with /plan and the plan primary agent, then hand off to build/auto through a structured review gate

VT Code is designed for both interactive development and unattended work. It keeps tool execution and provider access explicit, while allowing the same session to move from exploration to implementation and review.

Quick start

1. Install

The native installer is recommended for macOS and Linux. It installs VT Code and the ripgrep and ast-grep search tools used by its coding workflow.

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

Other installation methods are documented in the [Installation Guide](./docs/installation/README.md).

# Homebrew
brew install vinhnx/tap/vtcode

# Cargo
cargo install vtcode

2. Initialize a workspace

Run this from the project you want VT Code to work on:

cd path/to/your/project
vtcode init

This scaffolds project configuration and agent guidance. Review the generated files before committing them.

3. Configure a provider

Set the API key for the provider you want to use (or configure an OAuth-based provider with vtcode login). For example:

export OPENAI_API_KEY="sk-..."

See the [provider guides](./docs/providers/PROVIDER_GUIDES.md) for supported providers, local inference options, and authentication details. Never commit API keys or place them directly in vtcode.toml.

4. Launch VT Code

vtcode

VT Code opens an interactive terminal UI in the current workspace. Use ask, exec, or review when you want a one-shot workflow.

Common commands

vtcode                         # interactive TUI
vtcode init                    # scaffold project config + AGENTS.md
vtcode ask "explain Rc vs Arc" # one-shot question
vtcode exec "refactor main.rs" # headless task with full tool access
vtcode review                  # review uncommitted changes
vtcode update                  # self-update
vtcode webmcp serve --origin http://localhost:5173 --allowed-root /path/to/project

To connect a browser editor to the current interactive session, start vtcode in the target workspace and run /webmcp pair http://localhost:5173 in the TUI. For workspace-only browser access, use the vtcode webmcp serve command shown above. Both paths are disabled until explicitly started and keep browser writes behind the existing VT Code terminal or full-auto policy.

Documentation

Use the documentation by task: start with installation, then choose a user guide, integration guide, or reference.

Start here

• [Installation](./docs/installation/README.md): installation methods, provider setup, and troubleshooting
• [Getting started](./docs/user-guide/getting-started.md): first workspace, provider, and session
• Wiki: community wiki on configuration, providers, local models, skills, MCP, automation, security, and FAQ

User guides

• [Interactive TUI](./docs/user-guide/interactive-mode.md): primary agents, slash commands (/model, /review, /mcp, /skills, /theme, /compact)
• [CLI commands](./docs/user-guide/commands.md): command reference for interactive, headless, review, and automation workflows
• [WebMCP browser bridge](./docs/user-guide/webmcp.md): connect a supported browser editor to an active VT Code session or a bounded standalone workspace bridge
• [WebMCP deployment reference](./docs/reference/webmcp.md): public origins, pairing commands, origin-trial configuration, and deployment checks
• [Full automation](./docs/guides/full-automation.md): --full-auto CLI, plan-build-evaluate harness, subagents, and scheduled tasks
• [Providers](./docs/providers/PROVIDER_GUIDES.md): setup guides for all built-in providers
• [Configuration](./docs/config/CONFIGFIELDREFERENCE.md): vtcode.toml, tool config, and lifecycle hooks

Integrations

• [Agent Skills](./docs/skills/SKILLS_GUIDE.md): creating, loading, and sharing skills
• [Agent Plugins](./docs/guides/agent-plugins.md): portable skill + MCP packages via vtcode plugins
• [MCP Integration](./docs/guides/mcp-integration.md): client and server modes
• [Editor guides](./docs/guides/zed-acp.md): Zed ACP, VS Code, and Claude Code

Operations and architecture

• [Safety](./docs/security/SECURITY_MODEL.md): shell sandbox, security hardening, and threat model
• [Protocols](./docs/protocols/OPEN_RESPONSES.md): Open Responses, ATIF, A2A, and Anthropic Messages API
• [Loop engineering](./docs/project/PLAN-loop-engineering.md): worktree isolation, propose/verify, loop state, and cost guardrails
• [Planning workflow](./docs/guides/planning-workflow.md): /plan, review gate, and plan handoff to build/auto agents

Reference

• [Architecture](./docs/ARCHITECTURE.md): workspace boundaries and runtime design
• [Configuration field reference](./docs/config/CONFIGFIELDREFERENCE.md): complete vtcode.toml reference
• [Command security model](./docs/development/COMMANDSECURITYMODEL.md): execution policy and sandbox boundaries
• [Development setup](./docs/development/DEVELOPMENT_SETUP.md): prerequisites and local workflow
• [Testing](./docs/development/testing.md): test profiles and verification commands

Providers and models

VT Code supports 30 built-in providers, local inference backends, and custom OpenAI-compatible endpoints.

Provider directory

The list below is grouped by how a request reaches a model. The provider guide is the source of truth for credentials, supported capabilities, and model defaults.

| Category | Providers | | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Cloud LLMs | [Anthropic](./docs/providers/PROVIDERGUIDES.md#anthropic-claude) · [OpenAI](./docs/providers/PROVIDERGUIDES.md#openai-gpt) · [Gemini](./docs/providers/PROVIDERGUIDES.md#google-gemini) · [Meta AI (Muse)](./docs/providers/PROVIDERGUIDES.md#meta-ai) · [Z.AI](./docs/providers/PROVIDERGUIDES.md#zai-zai) · [Moonshot (Kimi)](./docs/providers/PROVIDERGUIDES.md#moonshot-kimi) · [StepFun](./docs/providers/PROVIDERGUIDES.md#stepfun) · [MiniMax](./docs/providers/PROVIDERGUIDES.md#minimax) · [Mistral](./docs/providers/PROVIDERGUIDES.md#mistral) · [Qwen](./docs/providers/PROVIDERGUIDES.md#qwen) | | Foundations | [NVIDIA NIM](./docs/providers/PROVIDERGUIDES.md#nvidia-nim) · [Xiaomi MiMo](./docs/providers/PROVIDERGUIDES.md#xiaomi-mimo) | | Gateways | [OpenRouter](./docs/providers/PROVIDERGUIDES.md#openrouter-marketplace) · [Merge Gateway](./docs/providers/PROVIDERGUIDES.md#merge-gateway) · [Evolink](./docs/providers/PROVIDERGUIDES.md#evolink-multi-model-gateway) · [HuggingFace](./docs/providers/PROVIDERGUIDES.md#huggingface) · [Atlas Cloud](./docs/providers/PROVIDERGUIDES.md#atlas-cloud) · [OmniRoute](./docs/providers/PROVIDERGUIDES.md#omniroute) | | Local inference | [Ollama](./docs/providers/PROVIDERGUIDES.md#ollama-local--cloud-models) · [LM Studio](./docs/providers/PROVIDERGUIDES.md#lm-studio-local-server) · [llama.cpp](./docs/providers/PROVIDERGUIDES.md#llamacpp-local-server) | | Other | [GitHub Copilot](./docs/providers/PROVIDERGUIDES.md#github-copilot) · [Anthropic API Compat](./docs/providers/PROVIDERGUIDES.md#anthropic-api-compatibility-server) · [Poolside](./docs/providers/PROVIDERGUIDES.md#poolside) |

Additional built-in providers include [DeepSeek](./docs/providers/PROVIDERGUIDES.md#deepseek), [xAI](./docs/providers/PROVIDERGUIDES.md#xai-grok), [OpenCode Zen](./docs/providers/PROVIDERGUIDES.md#opencode-zen), and [OpenCode Go](./docs/providers/PROVIDERGUIDES.md#opencode-go).

See the [Provider Guides](./docs/providers/PROVIDER_GUIDES.md) for credentials, model defaults, API capabilities, and setup details. Merge Gateway is a built-in OpenAI-compatible gateway with curated routes and pass-through support for valid explicit provider/model IDs.

Configure a provider

List available providers and configure one from the CLI:

vtcode models list
vtcode models config

For a quick start, set the environment variable documented by your provider. OAuth-based providers can use their dedicated vtcode login command.

Custom providers

Use [[custom_providers]] to add a private gateway, an aggregator such as Atlas Cloud or OmniRoute, or an internal inference cluster:

Basic configuration

[[custom_providers]]
name = "mycorp"
display_name = "MyCorp"
base_url = "https://llm.corp.example/v1"
api_key_env = "MYCORP_API_KEY"
model = "gpt-5-mini"
models = ["gpt-5-mini", "gpt-5.6-sol"]
context_window = 256000   # optional; defaults to 128000 tokens

Set the corresponding environment variable before launching VT Code:

export MYCORP_API_KEY="..."

Capability settings

• context_window: capability size in tokens. It controls UI context sizing,

compaction thresholds, and preflight token checks.

• models: optional model IDs to expose in the model picker. model remains

the default selection.

• api_format: optional value of auto, openai-chat, openai-responses, or

anthropic-messages. Omit it to preserve autodetection, or set it explicitly to prevent fallback to another format.

• Capability defaults include supports_tools, supports_reasoning,

supports_reasoning_effort, supports_vision, supports_structured_output, supports_parallel_tool_calls, supports_context_caching, supports_responses_compaction, and supports_context_edits.

The separate context.max_context_tokens setting can imp

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: vinhnx
• Source: vinhnx/VTCode
• License: Apache-2.0
• Homepage: https://vinhnx.github.io/VTCode/

Install and usage instructions live in the source repository linked above.