No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by adongwanai · Agent Tool · ★ 374
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is learn-workbuddy safe to install? View the security audit →
🔥 从0手搓桌面AI助手 · 24节课复刻WorkBuddy架构 一份开源教学蓝图 — 不是产品源码，是可以跑的 Agent 工程课。 模型是大脑，Harness 是操作系统。 📚 24章从 agent loop 到审计沙盒 📐 27张图每章一张架构图 ⚡ 1条命令离线跑完整链路 🔌 多ProviderDeepSeek/OpenAI/Anthropic ⭐ 如果这个项目对你有帮助，请给个 Star 支持我们继续出课！ 🤔 你是不是也被这些卡住了 你写过 CLI agent，能跑通 + tool calling，但一到桌面端就卡住了——工程复杂度翻 10 倍： 😫 会话常驻、恢复、重连 —— 不是"跑完就关"，是长期活着的进程 😫 工具太多时上下文窗口秒炸 —— 模型还没干活就 OOM 了 😫 工具输出几 MB —— 塞不进 context，模型直接摆烂 😫 长期记忆放哪里、什么时候注入 ——
| Stars | 374 |
| Forks | 59 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 63.5373308436154/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-23 |
| Created | 2026-07-08 |
| Platforms | python |
| Est. Tokens | ~17k |
Looking for a learn-workbuddy alternative? If you're comparing learn-workbuddy with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体
Bridgic is the next-generation agent development framework for building intelligent systems.
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing,
WorkflowAI is an open-source platform where product and engineering teams collaborate to build and iterate on
Polymcp provides a simple and efficient way to interact with MCP servers using custom agents
CaoGen — a vendor-neutral, local-first AI work desktop. Multi-provider agent runtime, GUI automation, MCP, Git
Explore other popular agent tool tools:
learn-workbuddy is 从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹. It is categorized as a Agent Tool with 374 GitHub stars.
learn-workbuddy is primarily written in Python. It covers topics such as agent-harness, ai-agent, anthropic.
You can find installation instructions and usage details in the learn-workbuddy GitHub repository at github.com/adongwanai/learn-workbuddy. The project has 374 stars and 59 forks, indicating an active community.
learn-workbuddy is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to learn-workbuddy on Agent Skills Hub include agent-craft, bridgic, LightAgent. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: