Probably the same reason as oh-my-zsh, you don't need 90% of it. Further compounding the problem in an agent harness is that you are polluting the context window by throwing the kitchen sink at it.
- it allows different models within one session via roles (I only have API, so pay per token)
- it's much more likely (ime) to use the LSP over grep for determining how code fits together
But I agree a 20k+ starting context is way overkill.
I find it's very hard to get information on harnesses people are using. I have to stay model agnostic so I avoid claude, codex, cursor, etc. I've used and tried opencode, which worked well, but obviously lacks the above features.
Does anyone have a resource for following what people are actually being productive with? With so much vibe going on it's hard to separate the wheat from the chaff.
Exactly! All these harness claims are just trust-me-bro, someone says omp is great for token saving, some other guy says it burns tokens...like dude which is it
usecomputer is a desktop automation CLI for AI agents. It works on macOS and Linux.
Screenshot, mouse control (move, click, drag, scroll), and keyboard synthesis (type and press) are all available as CLI commands backed by a native Zig binary
Mainly using playwriter.dev to help debug CSS issues on the page. It's an extension you can enable in Chrome and let agents control the browser via CDP
This one works as an extension so you don't need a new browser specifically for agents. It's easier to collaborate. Also if you run the MCP in non headless mode it brings to front the browser on every interaction, like opening a new page. With the extension this does not happen.
Another benefit is context usage.
The cli can also do a lot more than other MCPs because it uses code snippets run in a stateful sandbox to control the browser, so it can do virtually anything instead of just a few exposed tools like `scroll`, `click`