$ loading_
Learn how coding agents work under the hood and use them better.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "groundhog" yet — see the docs or source repo.
Explain from first principles how coding agents like Cursor understand requests, plan steps, use tools, and modify code. Use plain language to describe the overall workflow.
A beginner-friendly explanation covering request parsing, context reading, tool use, and code generation flow.
Give me an example showing the full execution chain of a coding agent fixing failing tests, including reading files, locating the issue, editing code, and validating results.
A step-by-step execution example that shows how the agent decides and acts in a real task.
Based on how coding agents work, summarize best practices for using Cursor effectively, including prompting, providing context, breaking down tasks, and checking results.
Actionable best practices that help users collaborate with coding agents more effectively and reliably.
Provide safe self-hosted web grounding for AI agents and crawlers.
Inject agent personas into Cursor chats to switch AI assistant roles quickly.
Lets MCP coding agents read and control browser pages with human-like actions.
Lets MCP coding agents read and control browser pages with human-like cursor behavior.
Use an extensible AI agent to install, run, edit, and test code.
Configure skills, tools, and AI coding agents from one capabilities.yaml file.