sopify 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 6.8 分,整体质量稳定。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
sopify 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。
sopify 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:pip 安装(推荐)
pip install sopify
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install sopify
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/evidentloop/sopify
cd sopify
pip install -e .
# 验证安装
python -c "import sopify; print('安装成功')"
# 命令行使用
sopify --help
# 基本用法
sopify input_file -o output_file
# Python 代码中调用
import sopify
# 示例
result = sopify.process("input")
print(result)
# sopify 配置文件示例(config.yml) app: name: "sopify" debug: false log_level: "INFO" # 运行时指定配置文件 sopify --config config.yml # 或通过环境变量配置 export SOPIFY_API_KEY="your-key" export SOPIFY_OUTPUT_DIR="./output"
<img src="./assets/logo.svg" width="120" alt="Sopify Logo" />
Resumable, traceable AI coding — decisions and history stay with the project
English · 简体中文 · Quick Start · Contributors
</div>
---
When facts are missing, Sopify stops and asks. When a decision needs your approval, it waits. When work is interrupted, it resumes from the last stopping point — even across different AI hosts.
Two-step install (recommended for first-time review):
curl -fsSL -o sopify-install.sh https://github.com/evidentloop/sopify/releases/latest/download/install.sh
sed -n '1,40p' sopify-install.sh
bash sopify-install.sh --target codex:en-US
Windows PowerShell:
iwr https://github.com/evidentloop/sopify/releases/latest/download/install.ps1 -OutFile sopify-install.ps1
Get-Content sopify-install.ps1 -TotalCount 40
.\sopify-install.ps1 --target codex:en-US
The repo-local install path remains available for developers and maintainers:
bash scripts/install-sopify.sh --target codex:en-US
python3 scripts/install_sopify.py --target claude:en-US --workspace /path/to/project
Install targets:
codex:zh-CNcodex:en-USclaude:zh-CNclaude:en-UScopilotThe protocol works with any host. Verified runtime integrations today:
| Host | Install target | Availability | Validation coverage | Notes |
|---|---|---|---|---|
codex | codex:zh-CN / codex:en-US | Deep verified | Host install flow, workspace bootstrap, and runtime package smoke are verified | Suitable for daily use |
claude | claude:zh-CN / claude:en-US | Deep verified | Host install flow, workspace bootstrap, and runtime package smoke are verified | Suitable for daily use |
copilot | Bootstrap via install.sh | Workspace ready | Workspace bootstrap, instruction distribution, and workspace marker are verified | Trigger wiring coming next |
Notes:
sopify status / sopify doctor for detailed capability claims and live diagnosticsAvailability expresses the current delivery tier, while Validation coverage describes what has already been validated| You want to… | Script | Command |
|---|---|---|
| Set up Codex / Claude | install.sh | As shown above — installs host prompt layer + Sopify payload |
| Set up Copilot | install.sh | curl -fsSL https://github.com/evidentloop/sopify/releases/latest/download/install.sh \| bash -s -- --target copilot |
install.sh --target codex:... / claude:... installs the selected host prompt layer and the Sopify payload. Most users do not need --workspace; that is an advanced prewarm path for maintainers or CI.install.sh --target copilot bootstraps the current workspace, creates .sopify-skills/sopify.json, updates .gitignore, and distributes Copilot instruction files. Pass --workspace <path> to target another repo, --language <lang> to control output language, or --no-copilot to skip Copilot files.bootstrap.sh remains available as a compatibility alias and forwards to install.sh --target copilot.For the full setup guide, see Getting Started. For a step-by-step demo, see External Repo Quickstart.
~go when you want Sopify to manage the full task workflow for you.status to see current progress, doctor to troubleshoot.python3 scripts/sopify_status.py --format text
python3 scripts/sopify_doctor.py --format text
will bootstrap on first project trigger: the host install is ready and the project-local runtime has not been prepared yetworkspace outcome: stub_selected [continue]: the workspace runtime entry is healthyglobal_bundle_missing, global_bundle_incompatible, or global_index_corrupted): repair the install and retrycurl -fsSL https://github.com/evidentloop/sopify/releases/latest/download/install.sh | bash -s -- --target codex:en-US
After install, use ~go to start a managed workflow. See Installation for other targets, platforms, and verification.
Already in a Sopify-managed repo? Open any AI host and continue the unfinished task — it picks up from where you left off. Full walkthrough →
| Step | What happens |
|---|---|
| Start | Ask the host to begin or continue a task |
| Pause | Sopify stops when facts are missing or a decision needs you |
| Resume | Work picks up from project state — even on a different host |
---
Start from the example config:
cp examples/sopify.config.yaml ./sopify.config.yaml
Most commonly used settings:
brand: auto
language: en-US
workflow:
mode: adaptive
require_score: 7
plan:
directory: .sopify-skills
Notes:
workflow.mode supports strict / adaptive / minimalplan.directory only affects newly created knowledge and plan directories| Command | Description |
|---|---|
~go | Automatically route and run the full workflow |
~go plan | Plan only |
~go exec | Advanced restore/debug entry, not the default user path |
~go finalize | Close out the current metadata-managed plan |
Most users only need ~go and ~go plan; maintainer validation commands live in CONTRIBUTING.md.
Delete or clear .sopify-skills/user/preferences.md; keep feedback.jsonl only if you still want the audit trail.
By default they live under .sopify-skills/ in the project root. To change that:
plan:
directory: .my-custom-dir
This only affects newly created directories; existing history is not migrated automatically.
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,sopify 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | sopify |
| 原始描述 | 开源AI工作流:Resumable, traceable AI coding — decisions and history stay with the project。⭐132 · Python |
| Topics | workflowadaptive-workflowai-agentai-codingclaudecodexpython |
| GitHub | https://github.com/evidentloop/sopify |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-22 · 更新时间:2026-05-22 · License:Apache-2.0 · 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