myPKA Agent工作流
经 AI Skill Hub 精选评估，myPKA Agent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 8.2 分，适合有一定技术背景的用户使用。
📚 深度解析
myPKA Agent工作流 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.2 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
myPKA Agent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。
📖 中文文档
myPKA Agent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。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 方式一：pip 安装（推荐）
pip install mypka
# 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 mypka
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/TomSolid/myPKA
cd myPKA
pip install -e .
# 验证安装
python -c "import mypka; print('安装成功')"
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 命令行使用
mypka --help
# 基本用法
mypka input_file -o output_file
# Python 代码中调用
import mypka
# 示例
result = mypka.process("input")
print(result)
# mypka 配置文件示例（config.yml） app: name: "mypka" debug: false log_level: "INFO" # 运行时指定配置文件 mypka --config config.yml # 或通过环境变量配置 export MYPKA_API_KEY="your-key" export MYPKA_OUTPUT_DIR="./output"
myPKA
An AI powered Personal Knowledge Assistance system, based on our business-proven ICOR methodology. Plain markdown. Any LLM. Yours forever.
myPKA is a folder. You drop it on your machine, point your LLM at it, and you have a six-specialist AI team that organizes your life end to end. It works on its own. No database to set up, no SaaS to log into, no vendor to lose your data to.
This scaffold is the basic structure you need to build your own AI team: the core agents everyone needs (Larry, Nolan, Pax, Penn, Mack, Silas), the folder architecture they operate on, the contracts that hold it all together, and the myPKA Cockpit: a local, navigable, wikilink-aware interface over your whole scaffold, included and free. It is free, and it stays free. From here you can build whatever you like on top: hire your own specialists through Nolan, or add ready-made Expansion Packs (the Designer Pack, the App Developer Pack, and more), which are part of the myICOR membership and install from the Expansion Packs page in the myICOR app. See Expansion Packs (membership) below.
Maintenance notice (2026-08): this repository's git history was re-initialized to a clean root as part of a privacy hardening pass. Published release artifacts are unchanged, and v5.5.1 remains byte-identical to its released ZIP. If you cloned this repository before this date, your clone's history has diverged: please re-clone, or rungit fetch originfollowed bygit reset --hard origin/main. The full release narrative lives on in CHANGELOG.md.
Watch on YouTube (newest first):
- My AI Team Now Has an Interface. All 12 Agents. One Folder. — the Cockpit launch
- Claude just killed ALL Note-Taking, Planner, and Health Apps. Here is proof. — the Cockpit reveal
- One Life. One Folder.
Why this is different from other scaffolds. Most folder structures are someone's preference dressed up as a system. myPKA is the working slice of ICOR, a methodology Paperless Movement S.L. and thousands of professionals world wide have been running their own business on for years. Every folder, every routing decision, every specialist contract maps to a piece of that framework. The structure is not arbitrary. The reasoning is teachable. Both matter when you scale past the first week.
What's new in v5.0.0
The scaffold returns to its basic shape: the six core specialists plus the myPKA Cockpit, free forever. Earlier downloads also bundled two agent packs into this repo. Those now live where the rest of the growing pack library lives: on the Expansion Packs page of the myICOR app, as part of the myICOR membership.
What this means in practice:
- This repo ships the base team: Larry, Nolan, Pax, Penn, Mack, Silas, with their contracts, SOPs, Workstreams, and Guidelines. Everything you need to run your knowledge, your journal, your CRM, and your tasks with an AI team. Nothing about the scaffold went paid.
- The myPKA Cockpit stays included and free, preinstalled at
Expansions/mypka-cockpit/. A local, navigable, wikilink-aware viewer over your whole scaffold (reads the SQLite mirror read-only). It runs entirely on your machine, uses your own Claude key, and never sends your data anywhere. No auto-launch — you generate a one-click launcher and start it yourself. - The Expansion mechanism stays built in.
Expansions/, the install Workstream ([[WS-003-install-an-expansion]]), and the authoring spec (Expansions/docs/expansion-spec.md) all remain, so any pack you download (or write yourself) drops in cleanly. - The Designer Pack (Iris, Charta, Pixel) and the App Developer Pack (Felix, Vex, Vera) are available with the myICOR membership on the Expansion Packs page, alongside new packs as they release.
- Why it's a MAJOR bump. The default download's team roster and SOP/Guideline set change shape versus the previous bundled download. If you already run a bundled folder, nothing is taken away from you: your installed packs are your state, they keep working, and they update through their own Expansion update paths.
Everything else carries forward: the task system, per-agent journals, the four-buckets-plus-Goals My Life doctrine, local version history, the self-updater, and the LLM-readable migration changelog. Plain markdown, any LLM, yours forever.
创新的多智能体协作框架，九人团队设计独特，代码质量良好。工程实践价值高，适合AI应用深度开发。
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- Python 依赖冲突：建议用 venv / uv 隔离环境
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- Python 依赖冲突：建议用 venv / uv 隔离环境
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
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。
🔗 相关工具推荐
❓ 常见问题 FAQ
AI Skill Hub 点评：myPKA Agent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 | myPKA |
| 原始描述 | 开源AI工作流：An AI-powered Personal Knowledge Assistance system with a nine-person AI team ba。⭐152 · Python |
| Topics | 多智能体AI工作流知识管理Claude集成开源 |
| GitHub | https://github.com/TomSolid/myPKA |
| License | NOASSERTION |
| 语言 | Python |
收录时间：2026-05-16 · 更新时间：2026-05-19 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。