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

41–50 of 51 posts

Re: A desktop app for isolated, parallel agentic development

#41

Post by ttoinou »

videlov wrote: post #31
plutonium3345 wrote: post #23

Earlier quoted context omitted.

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.

Are there automatic tools / command lines to run to try to recover work ? Would easy any problem

Re: A desktop app for isolated, parallel agentic development

#42

Post by ttoinou »

adastra22 wrote: post #33
_pdp_ wrote: post #12

Earlier quoted context omitted.

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.

To choose when to apply and not loose changes made by the agent

Re: A desktop app for isolated, parallel agentic development

#43

Post by videlov »

ttoinou wrote: post #41
videlov wrote: post #31

Earlier quoted context omitted.

(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.

Are there automatic tools / command lines to run to try to recover work ? Would easy any problem

The app has a built-in mechanism for going back in time (an operations log) which can be used for undoing situations that should not arise in the first place. It can be accessed via the app (there's a history tab) as well as via the CLI https://docs.gitbutler.com/commands/but-oplog

NB - the CLI version of GitButler is not yet at feature parity with the graphical version of the app yet

Re: A desktop app for isolated, parallel agentic development

#44

Post by adastra22 »

ttoinou wrote: post #42
adastra22 wrote: post #33

Earlier quoted context omitted.

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

To choose when to apply and not loose changes made by the agent

Yeah, you get that with git. What am I missing?

Re: A desktop app for isolated, parallel agentic development

#45

Post by ammario »

nojs wrote: post #7

This looks very useful. I would love something similar that lets me plug in actual Claude Code/Codex with their original agent loop, prompting etc, and just handles the multiplexing, worktrees, isolation, etc automatically (it looks like this tool doesn’t support that). Because I think a lot of the power of eg CC comes from the engineering they’ve done to the tool rather than the underlying model. How are people doin…

Author of Mux here:

I started building it out that way but found it very challenging to create parity between the models. E.g. they have different tools, system prompts, interruption semantics, cost tracking etc. The spirit of the product is decoupling the LLM from the UI, so we went with a custom loop / tools that can perform decently across all models.

Re: A desktop app for isolated, parallel agentic development

#46

Post by ammario »

foreigner wrote: post #36
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.

Curious to hear more.. why is random port selection not working for your case? The other issue we've seen is machines tend to get overloaded with tons of agents running tests concurrently, hence the SSH remote isolation mode.

Re: A desktop app for isolated, parallel agentic development

#47

Post by foreigner »

ammario wrote: post #46
foreigner wrote: post #36

Earlier quoted context omitted.

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.

Curious to hear more.. why is random port selection not working for your case? The other issue we've seen is machines tend to get overloaded with tons of agents running tests concurrently, hence the SSH remote isolation mode.

It's working, just a bit fiddly to setup.

Re: A desktop app for isolated, parallel agentic development

#48

Post by _pdp_ »

adastra22 wrote: post #44
ttoinou wrote: post #42

Earlier quoted context omitted.

To choose when to apply and not loose changes made by the agent

Yeah, you get that with git. What am I missing?

It is still git - but in memory. Why? Because we can and it is cool ;)

Re: A desktop app for isolated, parallel agentic development

#49

Post by nojs »

Coolin96 wrote: post #15
nojs wrote: post #7

This looks very useful. I would love something similar that lets me plug in actual Claude Code/Codex with their original agent loop, prompting etc, and just handles the multiplexing, worktrees, isolation, etc automatically (it looks like this tool doesn’t support that). Because I think a lot of the power of eg CC comes from the engineering they’ve done to the tool rather than the underlying model. How are people doin…

I’ve been using (and loving) https://github.com/raine/workmux which brings together tmux, git worktrees, and CLI agents into an opinionated workflow.

Thanks for posting this - just set it up and liking it so far
Post reply on HN