brandonchen

Proud to have helped edit an earlier draft of this — go Dexter go!

Thanks! Yup, so long as you don't have key bindings for meta-x and meta-c, you ought to be good in the terminal. We honor any repository's .gitignore and won't touch those files. We don't even let Codebuff know they exist, which has caused some issues with hallucinations in the past.

Making sure that our word is trustworthy to the broader world at large is going to be a big challenge for us. Do you have any ideas for what we can do? We're starting to think about open source, but we aren't quite ready for that yet.

It seems like we're all in our own tech bubbles more and more. Distribution is clearly a tough problem to crack, and no one in this space has really mastered it yet, aside from arguably Github Copilot.

No comment on YC here, but I think it's easy to criticize from the outside. I've personally have been impressed by all the peers, group partners, and alumni I've met so far. I'm biased, but I think YC knows what it's doing. Also, YC backs founders, not ideas.

Thanks! That's awesome to hear – if you wouldn't mind me asking, what was the context and tech stack of your side project? We love hearing about the wide variety of use cases people have found for Codebuff!

I assume you're referring to it guessing at what command you might type next? If so, the closest I can think of is Warp. Have you tried it?

Good question – here are a few reasons:

- It chooses files to read automatically on each message — unlike Cursor’s composer feature. It also reads a lot more than Cursor's @codebase command. - It takes 0 clicks — Codebuff just edits your files directly (you can always peek at the git diffs to see what it’s doing). - It has full access to your existing tools, scripts, and packages — Codebuff can install packages, run terminal commands and tests, etc. - It is portable to any development environment

We use OpenAI and Anthropic, so unfortunately we have to abide by their policies. But we only grab snippets of your code at any given point, so your codebase isn't seen by any entity in its entirety. We're also considering open-sourcing, so that might be a stronger privacy guarantee.

I should note that my cofounder James uses both and gets plenty of value by combining them. Myself, I'm more of a plain VSCode guy (Zed-curious, I'll admit). But because Codebuff lives in your terminal, it fits in anywhere you need.

No comment on our batchmates

brace yourself.

the night critics are coming.

Will do Also forwarding to our competitors, but something tells me they will ignore this.

> The sexy demos don't, in my opinion and experience, win over the engineers and leaders you need.

Great point, we're in talks with a company and this exact issue came up. An engineer used Codebuff over a weekend to build a demo app, but the CEO wasn't particularly interested even after he enthusiastically explained what he made. It was only when the engineer later used Codebuff to connect the demo app to their systems that the CEO saw the potential. Figuring out how to help these two stakeholders align with one another will be a key challenge for us as we grow. Thanks for the thought!

Tongue-in-cheek! No idea what you're talking about. But I appreciate the kind words :)

Ultimately, I think a future where the limit to good software is good ideas and agency to realize them, as opposed to engineering black boxes, mucking with mysterious runtime errors, holy wars on coding styles, etc. is where all the builders in this space are striving towards. We just want to see that happen sooner than later!

Beyond what James highlighted, I personally really like how simple Codebuff is. CLI tools tend to go a bit overboard with options and configurations imo, which is ok if you're just setting them up once or twice. But for a tool I want to rely upon every day for my work, I want them to be as simple as possible, but no simpler.

Have you used Aider extensively? How are you finding it for your coding needs vs IDE-based chats?

Thanks for sharing – I definitely want to plays with Aider more. My knowledge of it is limited, but IIRC Aider doesn't pull in the right files to create context for itself like Codebuff does when making updates to your codebase.

Another aspect is simplicity. I think Aider and other CLI tools tend to err towards the side of configuration and more options, and we've been very intentional with Codebuff to avoid that. Not everyone values this, surely, but our users really appreciate how simple Codebuff is in comparison.

Heh, this is an underrated comment.

Fundamentally, I think codegen a pretty new space and lots of people are jumping in because they see the promise. Remains to be seen what the consolidation looks like. With the rate of advancement in LLMs and codegen in particular, I wouldn't be surprised to see even more tools than we do now...

I'm sure your prompting is great! It's just hard because LLMs tend to be very wordy by default. This was something we struggled with for a while, but I think we've done a good job at making Codebuff take a more minimal approach to code edits. Feel free to try it, let me know if it's still too wordy/convoluted for you.