经 AI Skill Hub 精选评估,开源AI工作流 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 8.5 分,适合有一定技术背景的用户使用。
LLM维护的Markdown Wiki的治理层
开源AI工作流 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。
LLM维护的Markdown Wiki的治理层
开源AI工作流 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:go install(推荐) go install github.com/yazanabuashour/openclerk@latest # 方式二:从源码编译 git clone https://github.com/yazanabuashour/openclerk cd openclerk go build -o openclerk . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/yazanabuashour/openclerk/releases
# 查看帮助 openclerk --help # 基本运行 openclerk [options] <input> # 详细使用说明请查阅文档 # https://github.com/yazanabuashour/openclerk
# openclerk 配置说明 # 查看配置选项 openclerk --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 OPENCLERK_CONFIG="/path/to/config.yml"
The governance layer for LLM-maintained Markdown wikis. One binary. One SKILL.md.
OpenClerk gives coding agents a local, citation-bearing knowledge runtime over Markdown. Canonical Markdown stays the authority; generated indexes and optional modules stay derived.
Full install options live in docs/install.md.
Or tell your agent:
Install OpenClerk into $HOME/.local/bin from https://github.com/yazanabuashour/openclerk/releases/latest/download/install.sh only after gh attestation verify passes. Register release-matched skills/openclerk/SKILL.md. Verify command -v openclerk, openclerk --version, skill path, runner and skill.
Upgrade prompt:
Upgrade OpenClerk from https://github.com/yazanabuashour/openclerk/releases/latest/download/install.sh only after gh attestation verify passes. Re-register release-matched skills/openclerk/SKILL.md. Verify command -v openclerk, openclerk --version, skill path, runner and skill.
Bind a real vault after install:
openclerk init --vault-root path/to/vault
openclerk inspect
tmp_dir="$(mktemp -d)"
curl -fsSLo "$tmp_dir/install.sh" https://github.com/yazanabuashour/openclerk/releases/latest/download/install.sh
gh attestation verify "$tmp_dir/install.sh" --repo yazanabuashour/openclerk
OPENCLERK_INSTALL_DIR="$HOME/.local/bin" sh "$tmp_dir/install.sh"
openclerk demo init
openclerk demo ask "what changed and what is stale?"
The demo creates an isolated sample vault, changes a source note, and reports stale synthesis with citations and a repair request.
Install prompt:
Install the OpenClerk module <module-provider> using <module-manifest-path>. Use the resolved <module-command> path, register <module-skill-path>, and verify with `openclerk module` list_modules. Do not pass command_args or edit SQLite directly.
Upgrade prompt:
Upgrade the OpenClerk module <module-name> to <module-version-or-latest>. Refresh registration through `openclerk module`, preserve existing provider config, and verify with list_modules. Do not edit SQLite directly.
Available installable modules:
| Module name | Adds | Manifest | Skill |
|---|---|---|---|
ollama-embeddings | Semantic search (local-first) | modules/ollama-embeddings/module.json | modules/ollama-embeddings/skill/ollama-embeddings/SKILL.md |
gemini-embeddings | Semantic search (cloud opt-in) | modules/gemini-embeddings/module.json | modules/gemini-embeddings/skill/gemini-embeddings/SKILL.md |
tesseract-ocr | OCR review for images and scan-only PDFs | modules/tesseract-ocr/module.json | modules/tesseract-ocr/skill/tesseract-ocr/SKILL.md |
Core lexical search and citation behavior require no modules. Full module install guidance lives in modules/docs/install.md.
高质量的开源AI工作流项目
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:开源AI工作流 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 | openclerk |
| 原始描述 | 开源AI工作流:The governance layer for LLM-maintained Markdown wikis.。⭐9 · Go |
| Topics | AI工作流MarkdownWiki |
| GitHub | https://github.com/yazanabuashour/openclerk |
| License | MIT |
| 语言 | Go |
收录时间:2026-06-29 · 更新时间:2026-07-03 · 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