Has it gotten better and good enough? I tried it a few months back and it was pretty crappy. And it's not because of bad models (I used it with the latest Claude at that time) but because of poor harness implementation and UI.
Is it worth trying the latest version to see how it compares with Claude Code? I want OSS, model agnostic implementation to win but I felt the odds are off then. I'd be happy to be proven wrong.
I feel you and I also think this is a tough time. I routinely use Claude even though he typically ignores me ;) I'm also a maintainer of Goose and have been engaged since before the rust rewrite. I'll admit I don't get exactly what I want out of any agent. I also don't buy the "it is you" thing that is typical with Agents. We often need to know too many things and are defensive in how we act. I truly hope this is temporary.
ok back to the point. Block is not trying to sell a frontier model, or Goose at all. As an open source enthusiast, I like this model (no pun intended). Features go where the prominent site or key contributors want, vs a commercial agenda. To get more practical, it was goose folks themselves who put themsemselves out there in tbench.ai and remain in the top 10
Does this invalidate poor experience on use cases. no way. However, there's a lot of work being done by block folks to help teach and share practice and get things together. I'm always looking for pure local everything and Mic is also super keen on this, Today? well it is like watching someone type each character at a time while your laptop melts. I don't think this invalidates the long term, but it acknowledges the short term.
Next, Goose doesn't care about you in a specific way. Literally there is a Claude agent so you can swap out the goosey parts if you like. It is clunky and I'm personally looking into aligning that interop via Zed's ACP. I think like the combination of openness and not having any angle.. like not anti claude, literally give you a way to use it.. is telling.
This is a ramble and maybe a waste of your context, but I hope it colors some things and will get to see you around.
Adding a quick note as someone who contributes to Goose but isn’t a maintainer. I agree with a lot of what you’re saying. The harness and overall UX have changed quite a bit recently, though it’s still very much evolving like everything else in this space. If anyone tried it a while back, the newer versions are worth a look. And any issues people hit in practice are genuinely useful for us to improve things.
Instead, its strength tends to be a continued improvement over the long term, in a way that commercial software just can't sustain because it needs to show a return on investment.
I use OpenCode as my main CLI tool at this point, falling back to Claude Code and Codex as needed. It's really solid these days, highly recommend.
I use Claude Sonnet 4.5, Gemini 3 Pro Preview, and GPT 5/5-mini with great results on OC. I initially tried it so I could decouple from VS Code extensions while still using my Github Copilot plan like I had been with Roo Code/Kilo Code, but have branched out to also using it with the Claude Code backend and their free models as they come and go.
Definitely worth trying if you haven't picked it up recently.
I did tried as well few months and also uninstalled. Application didn't at least back then have update feature and for each new release you had to reinstall again. UI experience was also very poor comparing to many other open source projects - would expect they at least hire some designer
No. It didn't get any better. To be honest, the only working agentic tool out there in Claude Code. All other tools seems to confuse the model and not help much. Also bugs are a real problem (with gemini cli, it's really pathetic). Not that Claude Code doesn't have dozens of issues but the bar in this niche is set really low.
I've had decent experiences with Crush and GLM-4.6, I think the magic sauce is the fact that they have language server support that seems to make it somehow smarter.
TBH I mostly use it for very specific changes and not massive new features, those I do with Claude plan mode.
Has it gotten better and good enough? I tried it a few months back and it was pretty crappy. And it's not because of bad models (I used it with the latest Claude at that time) but because of poor harness implementation and UI.
Is it worth trying the latest version to see how it compares with Claude Code? I want OSS, model agnostic implementation to win but I felt the odds are off then. I'd be happy to be proven wrong.