Which can include type assertions but also a lot more. The agents seem to do well with this. I've also had good results using agents to write Crystal https://crystal-lang.org/ which is Ruby-like but does have the static types and produces blazing fast static binaries. Might be a sweet spot for coding agents if you're building some backend services. But I'd still pick Ruby on Rails for a new full stack project. - Source: Hacker News / about 2 months ago

Sounds a lot like Crystal, which is also similar to Ruby and features a green fiber runtime: https://crystal-lang.org/#concurrency. - Source: Hacker News / about 2 months ago

> 1. Go with a better type system. A compiled language, that has sum types, no-nil, and generics. I was looking for something like that and eventually found Crystal (https://crystal-lang.org) as a closest match: LLVM compiled, strong static typing with explicit nulls and very good type inference, stackfull coroutines, channels etc. - Source: Hacker News / 4 months ago

Wondering why https://crystal-lang.org/ hasn't been mentioned in the comments. - Source: Hacker News / 7 months ago

> What kind of code snippets could you suggest? Anything really! Some websites that do this currently: https://ziglang.org, https://crystal-lang.org and https://www.ruby-lang.org/en > I have a comparison table mentioning features Yes - I did see this in the README. Maybe worth adding it, or something similar to the website. - Source: Hacker News / 8 months 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 / 7 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 / 10 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 / 11 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 / 20 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 / 21 days ago