jedisct1

Keep sending all your secrets and giving full control of your devices to Anthropic.

This is fine.

The Claude plans (or whatever they’re called) are the only reason to use Claude Code.

Otherwise, it’s just obfuscated spyware that inserts ads into Git commits by default, and has been shown to consume far more tokens than other harnesses for the same tasks and models.

I really see no valid reason to use it. I tried a recent version to see whether things had changed since last year, and it’s just even more bloated.

It's written in Rust, so it's safe.

Not very hard... Rust wasm binaries are ginormous.

If you care about WASM performance, size and memory usage, Zig is a much better candidate.

Swival.dev has a tool to run Python code, and it can expose the MCP tools as Python functions.

This saves a couple prompts and tokens, but only in very specific cases, only with MCP servers that don't already support code mode, and only with large models.

In practice, I've not found that to make a real difference.

Plus, it's likely that more and more MCP servers are going to use code mode natively anyway.

Typescript is perfect for that kind of application. Plus, the same code runs everywhere, no need to ship native binaries for every OS and CPU.

Happy with swival.dev ...

You know, swival.dev is fully opensource, doesn't hide anything, fully supports GLM, has excellent context management to keep token usage low, and doesn't send anything you didn't ask to the cloud.