
GitHub Dungeons is a CLI extension written in Go that transforms a repository into a playable roguelike dungeon. Rooms, corridors, and enemies are generated from your codebase and rendered in the terminal; navigation uses arrow keys, WASD, or Vim keys, and the goal is to find the hidden door and escape five levels.
The dungeon layout is generated using Binary Space Partitioning (BSP)—a technique that recursively splits space into smaller regions, then connects them with corridors—and is seeded by the repository's latest commit SHA. This means the same codebase always produces the same map, but different repositories generate structurally distinct layouts, and the dungeon evolves as code changes.
The project was built using GitHub Copilot CLI's /delegate command, which hands tasks off to Copilot's coding agent running in the cloud to work asynchronously. This approach let the developer focus on game design and player experience (including easter eggs) rather than boilerplate and edge cases.
Installation is available via `gh extension install leereilly/gh-dungeons` for users with GitHub Copilot CLI already installed; features include fog of war, auto-attack, and stat tracking across five levels.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
The walkthrough points the CLI at a local mock via the ANTHROPIC_BASE_URL environment variable

A non-engineer operator says one person ships four smartphone apps on Google Play, three on the App Store, wit…

A Zenn guide explains systems to install before letting AI agents, bots or scheduled jobs post, send, publish…

A developer released agent-guardrails, a one-script Python standard-library plugin that guards Bash, Write, Ed…

Researchers at Microsoft published a paper titled "Adoption and Impact of Command-Line AI Coding Agents: A Stu…

Meta released open weights for Muse Spark Open, an 816B-parameter model built for coding and long-running agen…