AI Skill Hub 强烈推荐:Worktrunk工作流管理 是一款优质的Agent工作流。已获得 5.1k 颗 GitHub Star,AI 综合评分 8.2 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
专为AI代理并行工作设计的Git工作树管理CLI工具。支持多分支并行开发、Claude集成、自动化工作流编排。适合需要高效管理复杂项目的开发者和AI应用团队。
Worktrunk工作流管理 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。
专为AI代理并行工作设计的Git工作树管理CLI工具。支持多分支并行开发、Claude集成、自动化工作流编排。适合需要高效管理复杂项目的开发者和AI应用团队。
Worktrunk工作流管理 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 worktrunk # 方式二:从源码编译 git clone https://github.com/max-sixty/worktrunk cd worktrunk cargo build --release # 二进制在 ./target/release/worktrunk
# 查看帮助 worktrunk --help # 基本运行 worktrunk [options] <input> # 详细使用说明请查阅文档 # https://github.com/max-sixty/worktrunk
# worktrunk 配置说明 # 查看配置选项 worktrunk --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 WORKTRUNK_CONFIG="/path/to/config.yml"
WorktrunkJuly 2026: Worktrunk was released at the start of the year, and has quickly become the most popular git worktree manager. It's built with love (there's no slop!). Please let me know any frictions at all; I'm intensely focused on continuing to make Worktrunk excellent, and the biggest help is folks posting problems they perceive.
Worktrunk is a CLI for git worktree management, designed for running AI agents in parallel.
Worktrunk's three core commands make worktrees as easy as branches. Plus, Worktrunk has a bunch of quality-of-life features to simplify working with many parallel changes, including hooks to automate local workflows.
A quick demo:

### 📚 Full documentation at worktrunk.dev 📚
Homebrew (macOS & Linux):
brew install worktrunk && wt config shell install
Shell integration allows commands to change directories.
Cargo:
cargo install worktrunk && wt config shell install
<details> <summary><strong>Windows & other</strong></summary>
Windows. wt defaults to Windows Terminal's command, so Winget additionally installs Worktrunk as git-wt to avoid the conflict:
winget install max-sixty.worktrunk
git-wt config shell install
Alternatively, disable Windows Terminal's alias (Settings → Privacy & security → For developers → App Execution Aliases → disable "Windows Terminal") to use wt directly.
Arch Linux:
sudo pacman -S worktrunk && wt config shell install
Conda / Pixi (community-maintained feedstock):
conda install -c conda-forge worktrunk && wt config shell install
Or with Pixi: pixi global install worktrunk && wt config shell install.
</details>
Create a worktree for a new feature:
$ wt switch --create feature-auth
✓ Created branch feature-auth from main and worktree @ ~/repo.feature-auth
This creates a new branch and worktree, then switches to it. Do your work, then check all worktrees with wt list:
$ wt list
Branch Status HEAD± main↕ main…± Remote⇅ Commit Age Message
@ feature-auth + ↑ +27 -8 ↑1 +31 4bc72dc9 2h Add authenticat…
^ main ^⇡ ⇡1 0e631add 1d Initial commit
○ Showing 2 worktrees, 1 with changes, 1 ahead, 1 column hidden
The @ marks the current worktree. + means staged changes, ↑1 means 1 commit ahead of main, ⇡ means unpushed commits.
When done, either:
PR workflow — commit, push, open a PR, merge via GitHub/GitLab, then clean up:
wt step commit # commit staged changes
gh pr create # or glab mr create
wt remove # after PR is merged
Local merge — squash, rebase onto main, fast-forward merge, clean up:
$ wt merge main
◎ Generating commit message and committing changes... (2 files, +53, no squashing needed)
Add authentication module
✓ Committed changes @ a1b2c3d
◎ Merging 1 commit to main @ a1b2c3d (no rebase needed)
* a1b2c3d Add authentication module
auth.rs | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
lib.rs | 2 ++
2 files changed, 53 insertions(+)
✓ Merged to main (1 commit, 2 files, +53)
◎ Removing feature-auth worktree & branch in background (same commit as main, _)
○ Switched to worktree for main @ ~/repo
For parallel agents, create multiple worktrees and launch an agent in each:
wt switch -x claude -c feature-a -- 'Add user authentication'
wt switch -x claude -c feature-b -- 'Fix the pagination bug'
wt switch -x claude -c feature-c -- 'Write tests for the API'
The -x flag runs a command after switching; arguments after -- are passed to it. Configure post-start hooks to automate setup (install deps, start dev servers).
Rust实现的高性能Git工作树管理工具,针对AI代理工作流深度优化。5.1k星认可度高,活跃维护中,生态完整。
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
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。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
总体来看,Worktrunk工作流管理 是一款质量优秀的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | worktrunk |
| 原始描述 | 开源AI工作流:Worktrunk is a CLI for Git worktree management, designed for parallel AI agent w。⭐5.1k · Rust |
| Topics | Git管理AI代理工作流自动化Rust开发工具 |
| GitHub | https://github.com/max-sixty/worktrunk |
| License | NOASSERTION |
| 语言 | Rust |
收录时间:2026-05-20 · 更新时间:2026-05-30 · License:NOASSERTION · 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