#422 · Primary category: Education & Research
dsh-handbook
DeepSeek Harness (dsh) from 0 to 1 deep manual: installation, plugin development, performance tuning, real-world cases, and multi-agent comparison (Chinese + English PDF).
Project last updated:08/22/26
GitHub Stars
705
Forks
32
Contributors
8
License
Other
Why we included this project
DeepSeek Harness (dsh) is the official agent runtime from DeepSeek, built around an everything-is-a-plugin design, but the docs focus on architecture and skip the getting-started path. This handbook fills that gap with a Chinese-first, English-synced walkthrough: 15 chapters covering install, plugin development, and performance tuning, with every command actually run on a machine rather than sketched out. For anyone evaluating agent frameworks, the side-by-side comparisons of six mainstream agents and same-model benchmarks give a concrete sense of the trade-offs. A three-day learning roadmap and a one-page cheatsheet make it work as both a course and a quick reference. It is documentation, not runnable software, and dsh itself is still in pre-release, so the setup advice comes with that caveat; for anyone who actually wants to use dsh, though, this is the hands-on companion the official docs lack.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
JavaGuide
Java Interview & Backend General Interview Guide, covering computer fundamentals, databases, distributed systems, high concurrency, system design, and AI application development.
system-prompts-and-models-of-ai-tools
A curated collection of system prompts, internal tools, and AI models from popular AI assistants and coding agents.
30-seconds-of-code
Coding articles to level up your development skills
generative-ai-for-beginners
21 Lessons, Get Started Building with Generative AI