I'm a Claude Code Web fan and a rather heavy user. So I was interested in your product. However, I couldn't find an answer on the website. What parts did you find so good that you ported them?

Nothing groundbreaking but i'll do a blog writeup on the architecture if it would be helpful for people. My focus has been on mobile.

The main pieces I've integrated for mouse.dev inspired by claude/cursor was plan mode, agent questions, subagents, pre/post hooks, context compaction, repo-local skills, and permission modes. So mostly tools like enter_plan_mode, ask_user_question, and spawn_subagent, plus .mouse/skills and .mouse/plans.

One nice feature is continuity. If you’re working on desktop and save a plan to .mouse/plans, you can pick it up later on mobile with cloud agents, or do the reverse. You can plan something from your phone, then when you’re back at your desk, review it/build it. That was my initial goal with this project because I've found the plan act loop so helpful.

Mouse Cloud Agents is mostly an OpenCode-based harness, but everything routes through our MCP/event system so it’s mobile-first and provider-agnostic.

I intentionally skipped a lot of IDE and Claude Code style desktop features. The bet is that this new style of coding is becoming less “edit files in an IDE” and more steer a capable coding chatbot.

Would love to hear from anyone reading that's iterating on harness architecture, it's been really fun to work on.

There was already attempt for dav1d to re-implement in rust by rav1d. It was hard to match performance: https://www.memorysafety.org/blog/rav1d-perf-bounty/

> It was hard to match performance

They say it is 5% slower. That's close enough. I know they say it isn't but in reality that speed difference is just going to be used as an excuse by the anti-Rust crowd.

Not just performance, the code was littered with unsafe blocks and the benchmarks (IIRC) were gamed heavily by the Rust devs.

It was a dishonest effort that actually undermined the memory safety pitch.

Is it what CloudFlare Organization is about? https://blog.cloudflare.com/organizations-beta/

If the problem is excessive deployments via GitHub Actions, why not use concurrency control on GitHub Actions ( https://docs.github.com/en/actions/how-tos/write-workflows/c... ) instead of relying on agent randomness and the hope that it won't make the same mistake again? Am I missing something?

That feature was silent launched about week ago for me.

I use it to:

- perform review of latest changes of code to update my documentation (security policies, user documentation etc.)

- perform review to latest changes of code, triage them, deduplicate and improve code - I review them, close them with comments for over-engoneering / add review for auto-fix

- perform review of open GitHub issue with label, select the one with highest impact, comment with rationale, implement it and make pull request - I wake up and I have a few pull request to fix issues that I can approve /finish in existing Claude Code thread

I want also use it to: - review recent Sentry issues, make GitHub issues for the one with highest priority, make pull request with proposed fix - I can just wake up and see that some crash is ready to be resolved

Limit of 3 scheduled jobs is pretty impactful, but playing with it give me a nice idea on how I can reduce my manual work.

Maybe I’m missing the point but we have some of these implemented without the tool - the only one that needs an API key is the log scraping. It’s been surprisingly cheap and if we want to swap models we can.

Of course, this scheduled can be implemented on top of existing tools. However, it's incredibly convenient to have a UI where:

- you can easily edit the prompt

- you can see the prompt execution history

- you don't need any infrastructure to orchestrate it

- it works even when your computer is off

Once you start using it, it turns out to be very convenient.

CloudFlare for their serverless offering did it, and it works decent.

How are you performing backup of FerratDB? Are you using MongoDB tools, or are you using PostgreSQL-specific tools?

Nowadays universal answer for "what? why?" is AI. AI agent needs VMs to run generated code in sandbox as they can not be trusted.

I don't think everyone should assume that AI is the answer to all questions. I was asking the person I replied to, thanks.

You can install VSCode extension and use "/ide" to connect them.

Do people actually use this mode? Having to approve diffs in the ide is too annoying.

Depends on my task. If it’s complex and my expectation is for Claude to get things wrong the diff preview is helpful.

Even then, I'd wait until it's had a chance to iterate and correct itself in a loop before I'd even consider looking at the output, or I end up babysitting it to prevent it from making mistakes it'd often recognise and fix itself if given the chance.

True. I’ve been strictly in the terminal for weeks and I have a stop hook which commits each iteration after successful rust compilation and frontend typechecks, then I have a small command line tool to quickly review last commit. It’s a pretty good flow!

You can tell it not to do that and it will show inline diffs.

Snowflake uses it as primary database for their metadata. https://www.snowflake.com/en/blog/how-foundationdb-powers-sn...