As the author of QuickTile, which is written in Python but even closer to what you describe than a window manager would be, I have to say that, yeah, doing X11 stuff takes a lot of knowledge that's not ideally documented in non-print sources. Source: over 3 years ago

Actually, I plan to add a .nojekyll file and then use something like Pelican with custom plugins, then set GitHub Actions to run my update.sh on push... Similar to how http://ssokolow.com/quicktile/ is a Sphinx-based site hosted on GitHub Pages and automatically regenerated from the pushed sources. Source: about 4 years ago

I've been using ssokolow.com/quicktile for this purpose, it does what I need and doesn't replace the wm. Source: over 4 years ago

The best I could do for the API documentation for this project of mine was to use the automodule directive to autogenerate at the coarsest level possible and remember to never create new .py files if I could possibly avoid it. Source: almost 5 years ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 3 days ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 6 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 7 days ago

Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 16 days ago

If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 17 days ago