MIT-licensed Chinese AI knowledge base (VitePress) covering MCP, Agent and Harness Engineering guides — an ecosystem reference used alongside DeepSeek Harness, not installed as a dsh plugin.
DSH integration
Ecosystem-related
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
MIT
01What can it help you accomplish?
Look up AI tool guides, best practices and real-world experience for MCP, Agent, Skills, Prompt engineering and coding assistants
Searchable Markdown guides organized by category — claudeCode, cursor, mcp, Agent, Harness Engineering, prompt, rules, skills, vibe coding, AI interview prep and more
Developers using DeepSeek Harness and other AI coding tools who need practical reference material for MCP servers, skills and prompt/rules engineering
Run the knowledge base locally as a searchable documentation site
A local VitePress dev server serving the whole repository as docs, with built-in full-text search and a dark theme
Teams that want an offline copy of the AI pedia to browse or extend
02How to install into DeepSeek Harness
Prerequisites
- Node.js — the `start.sh` script automatically checks the Node version before installing dependencies
Installation steps
- 01
Clone the repository: `git clone https://github.com/Awesome-AI-Pedia/Awesome-AI-Pedia.git` then `cd Awesome-AI-Pedia`
$ git clone https://github.com/Awesome-AI-Pedia/Awesome-AI-Pedia.git
- 02
Grant execute permission on first run: `chmod +x start.sh`
- 03
Start with one command: `./start.sh` — it checks the Node version, installs dependencies and starts the dev server
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
Ecosystem knowledge base — a VitePress AI pedia covering MCP, Agent and Harness Engineering guides; it is browsed or self-hosted alongside DeepSeek Harness, not installed as a dsh plugin
Categorized AI knowledge directories
the repository's root-level category folders→Markdown guides per category: claudeCode, cursor, codex, mcp, Agent, Harness Engineering, prompt, rules, skills, 部署ai, vibe coding, Ai面试类 and more
Built-in local full-text search
search keywords in the VitePress site→full-text search results across all knowledge pages
Dark theme by default
the VitePress site UI→a dark interface enabled by default for long reading sessions
Automatic deployment to GitHub Pages
pushes to the `master` branch→the site is automatically built and published to GitHub Pages
every push to `master` triggers a GitHub Actions build and publish
04Who is it for? When not to use it?
Good for
- Developers using DeepSeek Harness and other AI coding tools who need practical reference material for MCP servers, skills and prompt/rules engineering
- Teams that want an offline copy of the AI pedia to browse or extend
Not for
- The README and knowledge-base content are written primarily in Chinese, so non-Chinese readers get limited value from the raw Markdown.
- The repository is very young (created 2026-08-03) with no releases, so content structure and guides may change rapidly.
05Compatibility, maintenance and safety notes
- The README and knowledge-base content are written primarily in Chinese, so non-Chinese readers get limited value from the raw Markdown.
- Local runs depends on Node.js and the bundled `start.sh` script; the README documents no alternative install path or minimum Node version number.
- The repository is very young (created 2026-08-03) with no releases, so content structure and guides may change rapidly.
MIT · actively maintained (last push 2026-08-19)
06Frequently asked questions
How do I use Awesome AI Pedia with DeepSeek Harness?
It is an ecosystem knowledge base, not a dsh plugin: you browse the guides online or run the site locally for reference while working with DeepSeek Harness. The README documents no direct dsh integration.
What topics does it cover?
Claude Code, Cursor, Codex, MCP practices (Figma, Playwright, Context7, Chrome DevTools and more), Agent, Harness Engineering, Prompt engineering, coding rules, Skills, AI deployment, vibe coding and AI interview prep.
How do I run it locally?
Clone the repository, run `chmod +x start.sh` once, then `./start.sh`. The script checks your Node version, installs dependencies and starts the VitePress dev server.
Is there an online version?
Yes — the site is automatically built and published to GitHub Pages on every push to `master`, and is available at awesome-ai-pedia.github.io/Awesome-AI-Pedia.
What language is the content in?
The README and knowledge-base articles are written primarily in Chinese.
07Related DSH workflows
dsh-context
by bowenliang123
Context dashboard tab + /context command showing context-window composition, per-turn history, compaction/prune events, per-message token costs
api-relay-audit
by toby-bridges
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
awesome-deepseek-harness-plugins
by zhiyuan-fan
Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.
jingyun-dsh
by jingyunstudio
A one-stop AI commercialization desktop client built on Jingyun Studio plus DeepSeek Harness (DSH).
08Data and sources
Awesome AI Pedia 是一个现代化 AI 知识库，旨在为开发者提供全面的 AI 工具使用指南、最佳实践和实战经验分享。
| [`mcp/`](./mcp) | Model Context Protocol：Figma / 蓝湖 / 飞书 / Playwright / Context7 / Chrome DevTools 等 MCP 实战 |
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.