1
In my experience, aider is the best out of the three. It has the least features too, but it "just works" the best. I tell the tool exactly what I want done and after learning a bit it goes and does that right like 90% of the time.
With aider-ce and opencode, I ran into way too many bugs. For example in Windows right now it seems that copy pasting just doesn't work, which is a massive loss of functionality when you can't copy paste important snippets to the model.
Opencode looks really cool as a TUI with the themes and such, but I really didn't like how random these agents are. I don't know if claude code and codex are like this too, but whatever simple task I give out could be solved right away or it could for some reason result in taking 5x as long as aider as it calls random tools, tries to do web searches for documentation that is technically correct but not the thing it needs, running into 403's probably because of bot detection, and then trying that 3 more times before it submits a worse patch than what aider would have made.
I'd just stick to aider, but aider-ce (community expansion) exists because the dev just kinda stopped working on it despite the fact that it has as many stars as opencode. Wondering if there are any better alternatives out there or maybe if others feel the same way about what's happening to aider. Its a shame because aider really is great at just applying AI just enough that I don't have to stress about its stochastic nature and it just does exactly what I asked no more no less. I feel like I have maximal control over AI running on my code with aider.
I uninstalled it and tried Cline, but I can't even get Cline to reliably open the chat on a simple CTRL+' (their default keybinding to pop open cline chat). So I promptly uninstalled that too. Curious if anyone here has tried something that has stood the test of time and could recommend it to me?
Really, all I want is an extremely streamlined AI chat experience that lets me stay in the drivers seat. I hate agents, I hate watching agents slowly process a task that I gave it that was designed to be extremely granular and small and still somehow the agent screws something up that I'll have to go in and fix anyways. I'd much rather just take the original experience I have with AI (chatgpt.com) and sort of answer the question of "How can I make the QnA/pair programming experience I get on chatgpt.com as fast and as embedded as possible in my own existing workflow so I can move as quickly as possible while staying in the driver's seat?" For me, continue's snappy CTRL+L keybinding to pop open chats with the highlighted context and typing @... to mention a file or two was the fastest thing that accomplished my requirements of staying in charge of what happens to the code (keeping the AI confined to a chat box).