Yeah, I think as agents become more capable, more isolation will be necessary. Hence, I also agree that either containers or VMs will eventually be required. We can see how tools like Cursor already have a built-in browser so that the agent can "see" (probably as text for now) what component you want to modify. In the future, I believe the workflow for an agent will be something like: [make changes] -> [get user input] -> [take a screenshot] -> [process the screenshot and user input] -> [make changes].
I doubt something like this can be implemented easily in a single environment without running into client and server port issues, etc.
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 development time. While git worktrees are not perfect, and they require extra space, it is easier for people to understand and easily locate this kind of structure while also being able to execute commands in a somewhat isolated environment. I would be happy if the app simply automates this for me and creates a new worktree, branch, and agent at that location as soon as I click 'Add agent'.
Then the only issues become merge conflicts between different branches... this is where extra dev time could be allocated, and implement agents that automatically merge branches.
(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.
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
I really like this, and I think you could even add some LLM features in there for more natural conversations.
The biggest issue I have is that it is a bit weird putting our startup ideas into someone else server. Is this open-source so we can self host? The central db for questions could still be curated by you in the repo, we would just pull to update the questions on our end. For new questions we would make PRs. You still decide which questions are good.
Thanks for the feedback! I love the idea of adding LLM features for natural conversation, but for now, I want to keep the tool 100% free and easy to use (no API key required). My main focus right now is helping founders master the standard rapid-fire YC questions through repetition.
Regarding privacy: You're totally right that founders are careful with their data. The good news is that the app is currently entirely front-end (client-side), with no backend at all. That said, I understand that people might still feel uncomfortable entering this information, so I’ve removed it. It will also make the process faster.
This is super nice. It works smoothly on mobile as well. Are there any tools you recommend for finding the coordinates by street address or business name?
I doubt something like this can be implemented easily in a single environment without running into client and server port issues, etc.