I tend to agree with you. I wrote 4 separate coding harnesses of my own earlier this year (in different programming languages, great learning experience), but pi running good local models like qwen 3.8 next flash, or a deepseek flash API from a vendor with decent privacy assurances is really the bedrock of my workflow. There are always exceptions: running pool harness with Laguna XS 2.1 6bit is a really nice local dev experience for code maintenance and quicker sessions. Also, I very occasionally really enjoy DeepSeek Harness with deepseek flash, CC with Opus 5.5 and agy with the latest Gemini Argon.

So there are many wonderful dev experiences, but generally relying on something relatively simple like pi makes a lot of sense, for my use cases.