Skip to content

Tutorials & Learning

# Project Growth Stars Description
1 dsh-handbook ⬆️ +39 ⭐604 From 0 to 1 handbook: installation, plugin development, performance tuning, real-world cases and same-model multi-agent comparisons (CN + EN PDF).
2 DeepSeek Harness Orange Book ⬆️ +24 ⭐1,118 Community Orange Book: complete system prompts, a 129-line startup checklist and three raw session logs — first-hand testing the official docs lack. Free PDF/EPUB/HTML.
3 dshfind ⬆️ +10 ⭐200 Learn DSH principles, plugin marketplace and best practices — from chapter-by-chapter Cordis paper reading to an auto-aggregated plugin market.
4 deepseek-harness-handbook ⬆️ +5 ⭐36 Independent, source-backed handbook for DeepSeek AI's official DeepSeek Harness (dsh): agents, plugins, security, troubleshooting, and runbooks.
5 dsh-harness-tutorial ⬆️ +2 ⭐54 DeepSeek Harness Agent 的原理与实现:从零到一实现一个 AI Agent —— 一切皆插件的中文教程(VitePress 站点 + 8 个 Demo + mini-harness 教学项目)

🔥 Top 10

# Project Stars Description Status
1 learn-harness-engineering ⭐14,556 Harness engineering beginner tutorial, from 0 to 1. ✅ active
2 DeepSeek Harness Orange Book ⭐1,118 Community Orange Book: complete system prompts, a 129-line startup checklist and three raw session logs — first-hand testing the official docs lack. Free PDF/EPUB/HTML. ✅ active
3 dsh-handbook ⭐604 From 0 to 1 handbook: installation, plugin development, performance tuning, real-world cases and same-model multi-agent comparisons (CN + EN PDF). ✅ active
4 dshfind ⭐200 Learn DSH principles, plugin marketplace and best practices — from chapter-by-chapter Cordis paper reading to an auto-aggregated plugin market. ✅ active
5 deepseek-harness-tutorial ⭐182 Detailed Chinese learning tutorial for DeepSeek Harness. ✅ active
6 dsh-memory ⭐66 白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。 ✅ active
7 dsh-harness-tutorial ⭐54 DeepSeek Harness Agent 的原理与实现:从零到一实现一个 AI Agent —— 一切皆插件的中文教程(VitePress 站点 + 8 个 Demo + mini-harness 教学项目) ✅ active
8 deepseek-harness-handbook ⭐36 Independent, source-backed handbook for DeepSeek AI's official DeepSeek Harness (dsh): agents, plugins, security, troubleshooting, and runbooks. ✅ active
9 dsh ⭐17 源码级拆解 DeepSeek Harness · 面向 Agent 开发者的中文学习资料 ✅ active
10 learn-deepseek-harness ⭐13 交互式教程:20 节课,从「模型只会说话」讲到写出能装进真实 DeepSeek Harness 的插件。含可跑 demo 与在线版。 ✅ active

Complete list (35)

Learning (35)

Project Stars Description Status
learn-harness-engineering ⭐14,556 Harness engineering beginner tutorial, from 0 to 1. ✅ active
DeepSeek Harness Orange Book ⭐1,118 Community Orange Book: complete system prompts, a 129-line startup checklist and three raw session logs — first-hand testing the official docs lack. Free PDF/EPUB/HTML. ✅ active
dsh-handbook ⭐604 From 0 to 1 handbook: installation, plugin development, performance tuning, real-world cases and same-model multi-agent comparisons (CN + EN PDF). ✅ active
dshfind ⭐200 Learn DSH principles, plugin marketplace and best practices — from chapter-by-chapter Cordis paper reading to an auto-aggregated plugin market. ✅ active
deepseek-harness-tutorial ⭐182 Detailed Chinese learning tutorial for DeepSeek Harness. ✅ active
dsh-memory ⭐66 白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。 ✅ active
dsh-harness-tutorial ⭐54 DeepSeek Harness Agent 的原理与实现:从零到一实现一个 AI Agent —— 一切皆插件的中文教程(VitePress 站点 + 8 个 Demo + mini-harness 教学项目) ✅ active
deepseek-harness-handbook ⭐36 Independent, source-backed handbook for DeepSeek AI's official DeepSeek Harness (dsh): agents, plugins, security, troubleshooting, and runbooks. ✅ active
dsh ⭐17 源码级拆解 DeepSeek Harness · 面向 Agent 开发者的中文学习资料 ✅ active
learn-deepseek-harness ⭐13 交互式教程:20 节课,从「模型只会说话」讲到写出能装进真实 DeepSeek Harness 的插件。含可跑 demo 与在线版。 ✅ active
deepseek-harness-whitepaper ⭐11 DeepSeek Harness 白皮书 · 131 页入门加进阶综合教程:从装上它、看懂它,到自己扩展它。面向想深入研究 agent harness 的开发者,所有结论回源码核对。 ✅ active
dsh-explain ⭐11 Local-first learning mode: cross-session global learning threads, explain-by-source, ExplainContext and compression. ✅ active
dsh-from-scratch ⭐10 A runnable TypeScript tutorial that builds a minimal DeepSeek-style agent harness from scratch. ✅ active
deepseek-harness-learning ⭐7 Learning website built from a systematic breakdown of the deepseek-harness repository, for developers curious how AI agent frameworks work. ✅ active
deepseek-harness-prompts ⭐6 DeepSeek Harness prompts for different modes. ✅ active
dsh-book-deepseek-harness ⭐6 'Deep Dive into DeepSeek Harness' — source-level architecture book: 37 chapter files, PDF, Mermaid diagrams and writing conventions. ✅ active
dsh-learning-mode ⭐6 A DeepSeek Harness (DSH) agent preset that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style. 学习模式 ✅ active
dsh-docs-panel ⭐5 DSH WebUI 里的「随身手册」:全局 Markdown 笔记,任何工作区随时可读。 ✅ active
dsh-learn-everything ⭐5 Feynman learning-mode plugin: teach → teach-back → judge → re-explain loop rendered as rich HTML lesson cards. ✅ active
dsh-plugin-lookatstudy ⭐4 dsh community plugin: turn any markdown/folder/GitHub learning repo into a guided AI-tutor course (gated skill tree, BKT mastery, SM-2 reviews) inside DeepSeek Harness ✅ active
gitlearnos ⭐4 Git-native AI learning OS with a GitLearnOS-exclusive DeepSeek Harness panel, targeted practice, local RAG, and learner-owned memory. ✅ active
mini-deepseek-harness-python ⭐4 Educational re-implementation of DeepSeek Harness in pure Python stdlib — event sourcing, plugin bus, agent loop. For learning only. ✅ active
dsh-deeptutor ⭐3 Learning assistant extension for DeepSeek Harness (dsh): brings DeepTutor tutoring to your agent — deep explanations, self-test questions, learning paths, personal knowledge-base search (RAG), and note archiving. 面向 DeepSeek Harness 的学习辅助扩展:为 agent 接入 DeepTutor 辅导能力 —— 深度讲解、自测题、学习路径规划、个人知识库检索(RAG)与笔记归档。
dsh-plugin-tutorial ⭐3 DeepSeek Harness 插件开发教程(中文):环境搭建、Cordis 基础、Tool 开发、事件系统、LLM 适配器、打包发布 ✅ active
deepseek-protocol-doctor ⭐2 Checks DeepSeek tool loops, reasoning_content, strict schemas and captured SSE; also works as a DSH plugin. ✅ active
dsh-agent-memory ⭐2 Self-evolving memory for DeepSeek Harness: capture → dream consolidation → retrieval injection → evolve. User profile, project memory, correction learning, resume narrative — with provenance back to the replayable session log. 自进化记忆插件。 ✅ active
dsh-habit ⭐2 Self-learning habit engine for DeepSeek Harness: correction signals, threshold judgment, two-level human gate · 自学习习惯引擎:观察纠正信号、阈值判断、两级人工门控 ✅ active
dsh-prompt-self ⭐2 个人 Prompt 画像引擎(DSH 双面客户端插件):消息级 prompt 自动改写 + 自动学习 + 可视化开关与画像 UI ✅ active
dsh-raven-research ⭐2 Source-grounded deep research, writing, and learning plugin for DeepSeek Harness (dsh): steerable checkpoints, mid-run steering, and citations verified against retrieved sources. ✅ active
dsh-plugin-tutorial ⭐1 Hands-on, screenshot-rich bilingual guide to DeepSeek Harness plugin development. DSH 插件开发实战指南(中英双语,全真实截图)。 ✅ active
dsh-preset-scaffold ⭐1 DeepSeek Harness Agent 预设:从零搭建标准化、可运行、可验证的项目骨架(架构师人设 + 六套模板资产 + 严格初始化流程)。 ✅ active
dsh-project-knowledge-review ⭐1 中文 DSH 知识复习插件:有证据才回答、资料缺失提醒补充学习视频。 ✅ active
dsh-starter-zh ⭐1 DSH 新手入门包:安装即得欢迎语、从 0 到 1 学习路径、按场景推荐插件、新手自查清单,并与 dsh-handbook-zh 中文教程联动。Starter pack for DeepSeek Harness beginners (Chinese). ✅ active
DeepSeek Harness Brain – Source-cited Obsidian knowledge base with a plain-English guide, architecture notes, an installable assistant skill, and portability guidance for DeepSeek Harness. ✅ active
dsh-plugin-practice – learn how to write cordis dsh plugin ✅ active