alsima

Thanks! Hopefully for synchronous tasks that would take CC/Codex >30 minutes we're looking for a ~30% speedup so feedback cycles are faster.

Hmmm couple things you can do I think OpenCode charges a subscription for models you can use in app without porting over a subscription or API key from CC/Codex, or you can charge enterprise clients, but that's something we'll have to figure out in the future, we're currently focused on making users happy.

We've since fixed this! There's now an options in settings to remove Bullet as an author.

Understood, sorry to hear that! We're actively working on a guest mode for people who prefer to not make an account.

We don't charge any subscriptions or fees. We're not open-source, but definitely considering it, has been highly requested. Business model TBD, right now we're focusing on making a product people love.

Hi that makes sense, and yes, will definitely review the security permissions requested by our Linux app, sorry to hear that it was hard to trust. We're definitely thinking about open-sourcing, it's been highly requested.

Yes, the CLI can run in Docker. The desktop app is not designed to run in Docker. And yes, you can use any HTTPS OpenAI-compatible endpoint, including a custom base URL and model ID.

Really cool that you built your own harness off of mini-swe-agent, we took a lot of inspiration from that. We're looking forward to trying out Sol Ultra Fast ourselves too! In our own experience, testing, building, searching, and other tool work still dominate a lot of time, but yes there could be a future where harnesses don't matter at all...but we expect Cerebras will also be super expensive :/

So sorry about that! We disabled download on iOS, but not Android (we'll fix that), it's not meant to be used on a phone (except for using our remote control feature).

No, we like that we're making this for ourselves as well!

Thanks! Yes, adding MCP support and preserving skills is definitely a priority for us right now.

Thanks for trying it! If you want to time it against Claude/Codex in app, we have a race lab you can use for that. Good to hear that the Linux support and integrated browser help.

Thank you so much!!

Agree, building real apps with the harness is the strongest proof. Would love to hear where Bullet fell short vs your setup, especially on speed for your builds.

We're actively working on implementing a guest mode feature right now for users that don't want to make an account. For reporting bugs, we have an in-app feedback form. Bugs are not automatically shared.

Yes, we saw this and it's really exciting, can’t wait to try it in Bullet. But faster inference only speeds up generation. In our own experience, testing, building, searching, and other tool work still dominate plenty of real tasks. We’ll have to test it in practice, but it’s a great development for everyone building agents.

No, we don’t support ACP today. Bullet uses its own internal harness and CLI integration. That said, we can definitely see it being something we work on in the future!

Thanks!

This is a great point, we're actively working on a fix.

If you’re up for giving it another shot, would love to hear other feedback on the app you have.

Thank you!

Mentioned in my comment above. Sorry, I thought you were talking about Gemini 3.6 Flash, not their new one. Yes, that's the reason why we didn't include the router in the benchmark to have a fair comparison of the harness itself.

Fair point, yes, the router is only in the live system (we'll try to make that more clear). We thought that comparing the router to other harnesses on the benchmark wouldn't be a fair evaluation because the speed/cost gains from our harness would mostly be from using cheaper and simpler models rather than actually having a better harness.

Thanks for the feedback, we do focus on good tool management, context efficiency, etc. As for routing, ideally it isn't the user who has to route themselves, but a layer that routes for them.

Thanks for the link to the repo! We have looked at things like https://github.com/Graphify-Labs/graphify but haven't had a chance to rigorously evaluate their speed boosts on our harness.

I think that if there are many players in the space, it's a problem worth working on! Like I said in the post, our main problem is speed and that's what we're trying to fix. It's been a problem, and it still is a problem. We have tried tools like OpenCode, Pi, etc. but for our speed issue, it did not fix it. If we go down dying on this boat, so be it, at least we went down dying on a problem we care about!

Like I mentioned, we omitted routing from the benchmark and evaluated with our strongest model modality. Also, randomly selecting between Fable and Gemini 3.7 Flash wouldn't preserve quality.

We're optimizing every day :)

The benchmark wasn't evaluated with the router, we wanted an apples-to-apples comparison of our harness against other harnesses like mini-swe-agent on the same models to see if we added speed + cost value beyond routing.

We'll get on that :)

Thanks for bringing this up and trying it out! We've disabled Cmd+Option+I in the new version and also have a message during signup about sharing chats with Bullet, let us know if you run into any other issues!

Thanks for the detailed feedback, this was really valuable.

We fixed file autocomplete, automatic CLAUDE.md loading for Claude subscription sessions, and the plan issues. Plans now only appear when requested, and progress only updates after the related work has actually been done.

Your comparison with Claude Code is fair. Speed remains something we're trying to optimize outside of benchmarks, and long running tasks with plans seems to be something we need to improve. We're actively working on more optimization to latency and unnecessary model calls.

Thanks again for the comment and if you could try the latest build when you have time, would love to hear your thoughts again!