经 AI Skill Hub 精选评估,VT代码 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
VT代码 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
VT代码 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:cargo install(推荐) cargo install vtcode # 方式二:从源码编译 git clone https://github.com/vinhnx/VTCode cd VTCode cargo build --release # 二进制在 ./target/release/vtcode
# 查看帮助 vtcode --help # 基本运行 vtcode [options] <input> # 详细使用说明请查阅文档 # https://github.com/vinhnx/VTCode
# vtcode 配置说明 # 查看配置选项 vtcode --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export VTCODE_CONFIG="/path/to/config.yml"
<img src="./resources/logo/vt_code_adaptive.svg" alt="VT Code" width="600" />
Plan, change, and verify code from your terminal, with every step auditable.
VT Code is an open-source coding agent for your repository. Choose the model, keep tool calls under policy, and review every change.
<a href="https://deepwiki.com/vinhnx/vtcode"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
<img src="./resources/gif/vtcode.gif" alt="VT Code demo: plan, then review changes in the terminal" width="76%" /> </div>
VT Code runs in your terminal and works on your repository: explore, plan, edit, and verify with the model you choose. It owns context, tool calls, and execution policy, so long tasks stay auditable and resumable.
| At a glance | What you get |
|---|---|
| **Planning** | [Plan read-only](./docs/guides/planning-workflow.md), then review turn diffs. |
| **Safety** | [Auditable command policy](./docs/security/SECURITY_MODEL.md) and sandboxing. |
| **Self-correct** | [HOVER loop](./docs/development/hypothesis-revision-validation.md) on tool mismatch. |
| **Long runs** | [Headless exec](./docs/user-guide/exec-mode.md) with compaction and resumption. |
| **Integrations** | [MCP](./docs/guides/mcp-integration.md), Skills, plugins, and editor bridges. |
| **Models** | [Hosted or local providers](./docs/README.md#provider-index) per task. |
Every loop states the expected outcome, gathers bounded evidence, and revises only when the evidence disagrees. See the HOVER acceptance table for the full contract.
vtcode schedule create --name "weekly-dep-audit" \ --cron "0 9 1" \ --prompt "Check for outdated dependencies and report known vulnerabilities" ```
```bash
curl -fsSL https://raw.githubusercontent.com/vinhnx/VTCode/main/scripts/install.sh | bash
The installer also attempts to add the optional `ripgrep` and `ast-grep` search tools. To manage installation
yourself, use Homebrew or Cargo:
bash brew trust vinhnx/tap brew install vinhnx/tap/vtcode
cargo install vtcode
On Windows, install with PowerShell; Windows artifacts are best-effort and may lag behind macOS/Linux:
powershell irm https://raw.githubusercontent.com/vinhnx/VTCode/main/scripts/install.ps1 | iex ```
Run vtcode --version to verify the installation. The installation guide covers prerequisites, other install methods, and optional search tools.
Requirements: macOS, Linux, or Windows/WSL. Building from source needs Rust 1.98.1+ (edition 2024).
Common commands:
| Goal | Command |
|---|---|
| Start the TUI | vtcode |
| Ask without tools | vtcode ask "explain Rc vs Arc" |
| Run a task headlessly | vtcode exec "refactor main.rs" |
| Review pending changes | vtcode review |
| Schedule recurring work | vtcode schedule create --prompt "..." --every 1h |
| Resume the last session | vtcode continue |
| Inspect a run log | vtcode trajectory |
In your project directory, scaffold the configuration and agent instructions, then add credentials for your provider. For example, to use OpenAI:
cd path/to/your/project
vtcode init # scaffolds config + AGENTS.md; review before committing
vtcode secret add openai # stores your OpenAI API key in secure storage
Replace openai with your provider. vtcode secret add uses secure storage (OS keyring or encrypted file). You can also set credentials in environment variables or a workspace .env file, or use vtcode login if your provider has a supported login flow. See Getting started and Provider guides for provider-specific instructions.
[!NOTE] ChatGPT OAuth reuses the Codex CLI's public client identity via an unofficial compatibility flow; prefer your own OpenAI API key. GitHub Copilot uses the official copilot CLI. See OAuth authentication.
[!CAUTION] Keep API keys out of Git andvtcode.toml. If you use a workspace.envfile, make sure it is not committed.
环境依赖与系统要求
安装步骤说明(含 Docker/pip/源码等部署方式)
配置说明(含 MCP / env / 关键参数)
API/接口说明
工作流 / 模块说明
高质量的开源AI工作流,具有强大的代码理解能力
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:VT代码 的核心功能完整,质量优秀。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | VTCode |
| 原始描述 | 开源AI工作流:VT Code is an open-source coding agent with LLM-native code understanding and ro。⭐648 · Rust |
| Topics | AIRust代码理解 |
| GitHub | https://github.com/vinhnx/VTCode |
| License | MIT |
| 语言 | Rust |
收录时间:2026-05-31 · 更新时间:2026-05-31 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端