Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A desktop app for isolated, parallel agentic development

github.com

Post reply on HN
Print view View original

31–40 of 51 posts

Re: A desktop app for isolated, parallel agentic development

#31

Post by videlov »

plutonium3345 wrote: post #23
ttoinou wrote: post #2

Something I never see mention is that all agents / CLI tools seem to modify local files. Which makes editing current files, working with the git, asking to only modify some parts of the files etc. cumbersome, as the agent is constantly reading and writing to files that we are also accessing. This is usually solved by using git worktree but this solution requires 1 new folder name and branch for each new agent, and ea…

I personally have had a frustrating experience with GitButler, and would prefer if things don't become too complicated. For example, when you accidentally break GitButler, it can become really difficult to recover all your unpushed progress. It is also hard to find the exact location of where your code changes are stored across different branches. My suggestion would be to keep things simple, pragmatic, and save deve…

(co-founder of gb here) I am really sorry for the frustration - the app should do better and we will do better. In the past few months we have been putting a very deliberate effort to eliminate all conditions from which such poor experience can come about.

The work is not complete but we have stability and correctness as a primary goal, and something that is a requirement for us to declare a v1.0.

Re: A desktop app for isolated, parallel agentic development

#32

Post by videlov »

undeveloper wrote: post #28
ttoinou wrote: post #2

Something I never see mention is that all agents / CLI tools seem to modify local files. Which makes editing current files, working with the git, asking to only modify some parts of the files etc. cumbersome, as the agent is constantly reading and writing to files that we are also accessing. This is usually solved by using git worktree but this solution requires 1 new folder name and branch for each new agent, and ea…

gitbutler is neat, but doesn't separate out files -- the changes are still visible to other sessions

You are right - it is something we did intentionally, but I would like to learn more from your use case - what is the reason to prefer isolation of changes?

Is it the case that you wish to have multiple agents working on the same task and then picking the best implementation? Or do you have a reason to prefer multiple tasks to be implemented in complete isolation from one another?

Re: A desktop app for isolated, parallel agentic development

#33

Post by adastra22 »

_pdp_ wrote: post #12
ttoinou wrote: post #2

Something I never see mention is that all agents / CLI tools seem to modify local files. Which makes editing current files, working with the git, asking to only modify some parts of the files etc. cumbersome, as the agent is constantly reading and writing to files that we are also accessing. This is usually solved by using git worktree but this solution requires 1 new folder name and branch for each new agent, and ea…

Given that all of these agents are written in javascript I have always wondered why they cannot simply use https://isomorphic-git.org/ and do everything in memory.

Why is in-memory a selling point? You want a record on disk.

Re: A desktop app for isolated, parallel agentic development

#34

Post by adastra22 »

Seattle3503 wrote: post #16

The issue I run into is with integration tests that rely on docker. If two agents try to run tests at the same time it doesn't work. I need to manually do air traffic control on the agents use of higher level tests suites.

I don't understand. Why is docker an issue?

Re: A desktop app for isolated, parallel agentic development

#35

Post by ryandv »

CGamesPlay wrote: post #22
ttoinou wrote: post #2

Something I never see mention is that all agents / CLI tools seem to modify local files. Which makes editing current files, working with the git, asking to only modify some parts of the files etc. cumbersome, as the agent is constantly reading and writing to files that we are also accessing. This is usually solved by using git worktree but this solution requires 1 new folder name and branch for each new agent, and ea…

> While it can be super powerful, I wish there was a quicker "in memory" agent solution where each agent keeps in its own RAM the list of files modifications ("patch") it recommends to apply to solve current issue. Then we could apply that patch depending on what we're doing, if we have others patches to apply before etc. Then the changes can't be tested to even verify that they pass the compiler/linter, much less te…

> or a hacky, vibe-coded, in-memory VFS

ramfs still exists, you know.

Re: A desktop app for isolated, parallel agentic development

#36

Post by foreigner »

Seattle3503 wrote: post #16

The issue I run into is with integration tests that rely on docker. If two agents try to run tests at the same time it doesn't work. I need to manually do air traffic control on the agents use of higher level tests suites.

Struggling with the same thing right now. I'm trying to make it work by generating unique ports for each instance so they don't conflict. Not quite 100% successful yet.

Re: A desktop app for isolated, parallel agentic development

#37

Post by foreigner »

I've been using Catnip for this: https://github.com/wandb/catnip

Very similar features, Catnip is Claude Code specific and does everything in a Docker container so you can more safely run in YOLO mode and the Git worktrees don't make a mess on your host filesystem or checkout. Also is mobile responsive which is cute.

Re: A desktop app for isolated, parallel agentic development

#38

Post by CGamesPlay »

ryandv wrote: post #35
CGamesPlay wrote: post #22

Earlier quoted context omitted.

> While it can be super powerful, I wish there was a quicker "in memory" agent solution where each agent keeps in its own RAM the list of files modifications ("patch") it recommends to apply to solve current issue. Then we could apply that patch depending on what we're doing, if we have others patches to apply before etc. Then the changes can't be tested to even verify that they pass the compiler/linter, much less te…

> or a hacky, vibe-coded, in-memory VFS ramfs still exists, you know.

When you set out to implement what GP is talking about with ramfs, you're either going to use git worktrees to do it, or reinvent them.

Re: A desktop app for isolated, parallel agentic development

#39

Post by mbreese »

chrisweekly wrote: post #14
ttoinou wrote: post #4

Earlier quoted context omitted.

Docker is very heavy and more for Linux, I'm on macOS and Windows for desktop software development and can't put my software to test inside Docker. But yeah I could have sandboxes inside macOS and inside Windows (virtualization, VMs, WSL etc.), I'd still need one main orchestrating agent + GUI to rule them all

Not 100% sure it will solve your complaints about Docker, but https://OrbStack.com makes working w/ docker, docker-compose, linux vms, and k8s so much better.

I’m pretty sure they were referring to building macOS or Windows desktop programs, which Docker doesn’t help with.

Re: A desktop app for isolated, parallel agentic development

#40

Post by ttoinou »

videlov wrote: post #30
ttoinou wrote: post #2

Something I never see mention is that all agents / CLI tools seem to modify local files. Which makes editing current files, working with the git, asking to only modify some parts of the files etc. cumbersome, as the agent is constantly reading and writing to files that we are also accessing. This is usually solved by using git worktree but this solution requires 1 new folder name and branch for each new agent, and ea…

(co-founder of GitButler here) We chose not to use separate git worktrees under the hood for this functionality. Let me try to break down why, maybe there's an opportunity for me to learn more here. In my head I separate between use cases of 1) "different tasks" and 2) "best of n, same task". The app that we built already had the ability to separate changes into branches while in the worktree (on disk) it renders the…

Thanks! That’s an interesting feedback I’ll try GitButler again. You know more than me so I can’t answer
Post reply on HN