#529 · Primary category: Education & Research
learn-agents-from-opencode
根据 opencode 源码编写的 agent 开发教程
Project last updated:04/30/26
GitHub Stars
506
Forks
50
Contributors
4
License
MIT
Why we included this project
OpenCode is a complete open-source coding agent, and these tutorials work through its source code file by file to show how such a project is really put together. The lessons cover system prompt assembly with provider adaptation and environment injection, how permission rules and tool call flows fit into the request path, and the session and iteration loops that keep an agent from spinning. Each tutorial points to the matching files in the bundled OpenCode submodule, so you can read the explanation with the actual implementation open beside it. That makes the series useful for developers who want to build a controllable agent and would rather study a design that already runs in the real world than work out the architecture from scratch. One thing to know up front: the tutorials are written in Chinese.
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