louiskw

Vibe Kanban (YC S21) | Rust + TypeScript | Open Source | London, UK (onsite) | Full-time | £80–120k + 0.5%

We're building the platform for engineers who spend most of their time planning and reviewing code written by AI. We’re hiring for two senior roles:

Frontend (TypeScript, React): https://jobs.polymer.co/vibe-kanban/36855?source=hn

Backend (Rust): https://jobs.polymer.co/vibe-kanban/36873?source=hn

The project is open source — check it out here: https://github.com/BloopAI/vibe-kanban

Are you sure you're using vibe-kanban? The project spins up a worktree for each task attempt specifically to solve this problem.

Merged and building, thanks for bearing with us

I would say conservatively that 80% of Vibe Kanban has been built by Amp

That's fair feedback, I have a PR with a very clear opt-in here https://github.com/BloopAI/vibe-kanban/pull/146

I will leave this open for comments for the next hour and then merge.

Interesting, hadn't heard of that. Would better GitLab support be useful in Vibe Kanban?

Very much a bet that things are going to get much much better very quickly

Yes I generally cherry pick the easier 50% of my backlog and work on those with Vibe Kanban, and the other 50% is still manual or happens with coding agent but with a human-in-the-loop.

This is a bet that coding agents will continue to get better, and this feels like the right time to try and figure out the interface.

I could see there being a long term free offering that doesn't cost us compute or tokens, and probably some other offerings that actually do use resources and would make sense to build a business around.

But that's not a today problem, we just want to absorb feedback and iterate until we build the ultimate tool for working with these coding agents.

Kanban seems like a good starting place, but I broadly agree that the interface for human<>agent collaboration will need to be different from the default interface we have today with legacy PM tools.

Things move across the board so quickly when AI is doing the work that ~50% of the columns seem pretty redundant.

It can open GitHub PRs from the interface and there's tons more info we want to pull in like the result of CI checks

Good point - there are a few random ones already but I will ask a coding agent to implement this comprehensively

"11 days ago" this feels like a year ago :O

For me, the average task takes a coding agent 2-5 minutes to complete. A slightly annoying amount of time as I'm prone to getting distracted while I wait.

This gives me something to do in that time.

My guess is time to complete a task will oscillate - going up as we give agents more complex tasks to work on, and going down with LLM performance improvement.

Great ChatGPT question XD

Cheers! Smaller teams, more infrastructure, more testing, tasks requiring review in minutes not days - the features are just totally different for the new world than what legacy PM tools are optimised for, and who they have to continue to serve.

Nostalgia!

Let me know if any issues, we're turning feedback around pretty quick

This is a bet on a future where code is increasingly written by AI and we as human engineers need the best tools to review that work, catch issues and uphold quality.

Yeah I think giving the option to move execution to the cloud makes a lot of sense, I already find my macbook slowing down after 4 concurrent runs, mainly rustc.

Also now we're pushing many more PRs think we defo need better ways to stack and review work. Will look into this asap

bloop (YC S21) | Product Engineer (Rust, AI) | Onsite London, UK

We're combining LLMs and transpilers to translate COBOL into Java. If you’re getting into (or already work in) Rust, and have a strong product mindset, this role could be a great fit. Come and build LLM pipelines and agents, that help the largest companies modernise their legacy codebases.

Please email join [at] bloop [dot] ai with "HN Product Engineer" in the subject line.

More details - https://www.ycombinator.com/companies/bloop/jobs/iCrEllp-pro...

https://github.com/BloopAI/bloop Is fully open source and has full text + regex search built on tantivy fyi

bloop (YC S21) | Software Engineer (Rust, Compiler) | Hybrid London, UK

We're building automatic code translation software, combining source to source compilers and LLMs. If you're into tree-sitter, ANTLR, ASTs or compilers we should speak. Rust proficiency is also a must.

Please email join [at] bloop [dot] ai with "HN Rust Compiler Engineer" in the subject line.

Pretty interesting, and rare to see projects in the space written in Fortran. Would be interested to hear what the advantages are, and appreciate if it's simply a case of personal preference too!