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.

Great idea! We were kicking around something like this, but couldn't get it ready in time for today's launch – but keep your eyes peeled! Our Discord community is a great place to stay up to date.

Yup, I had the same thought. I just ran into an issue during today's launch and used Codebuff to help me resolve it: https://www.tella.tv/video/solving-website-slowdown-with-ai-.... Next time, I'll try to record before I start working, but it's hard to rememeber sometimes.

Ah, good catch. We (read: I) introduced a bug that gave customers $500 worth of credits in a month as opposed to the $100 they paid for, and this user saw that and took advantage. Needless to say, we fixed the issue and added more copy to show to users when they _do_ exceed their thresholds. We haven't had that issue since. And of course, we ate the cost because it was our (expensive!) mistake.

The user had spent the entire weekend developing the app, and admitted that he would have been more careful to manage his Codebuff usage had it not been for this bug.

We're open to adding hard limits to accounts, so you're never charged beyond the credits you paid for. We just wanted to make sure people could pay a bit more to get to a good stopping point once they passed their limits.

Amazing, glad it worked well for you! I main VSCode but tried Zed in my demo video and loved the smoothness of it.

Totally understand where you're coming from, I personally use it in a terminal tab (amongst many) in any IDE I'm using. But I've been surprised to see how different many developers' workflows are from one another. Some people use it in a dedicated terminal window, others have a vim-based setup, etc.

Nice, super simple. We're definitely fitting into this definition of RAG then!

Gotcha – so broadly encompasses how we give external context to the LLM. Appreciate the extra note about vector databases, that's where I've heard this term used most, but I'm glad to know it extends beyond that. Thanks for explaining!

Thanks for being an early user and supporter! You've helped us catch so many issues that have helped us get the product to where it is today!

FWIW I don't find that I'm losing good engineering habits/thought processes. Codebuff is not at the stage where I'm comfortable accepting its work without reviewing, so I catch bugs it introduces or edge cases it's missed. The main difference for me is the speed at which I can build now. Instead of fussing over exact syntax or which package does what, I can keep my focus on the broader implications of a particular architecture or nuances of components, etc.

I will admit, however, that my context switching has increased a ton, and that's probably not great. I often tell Codebuff to do something, inevitably get distracted with something else, and then come back later barely remembering the original task

Hah no, you're not alone! Candidly, this is one of the top complaints from users. We're doing a lot of prompt engineering to be safe, but we can definitely do more. But the ones who take the leap of faith have found that it speeds up their workflows tremendously. Codebuff installs the right packages, sets up environments correctly, runs their scripts, etc. It feels magical because you can stay at a high level and focus on the real problems you're trying to solve.

If you're nervous about this, I'd suggest throwing Codebuff in a Docker container or even a separate instance with just your codebase.

Genuine question: at what point does the term RAG lose its meaning? Seems like LLMs work best when they have the right context, and that context must be pulled from somewhere for the LLM. But if that's RAG, then what isn't? Do you have a take on this? Been struggling to frame all this in my head, so would love some insight.

Thanks for being one of our early users and dealing with our bugs! I love that we can fit into so many developers' workflows and support them where _they are_, as opposed to forcing them to use us for everything.

Cruft that built up over time But you make a good point, I'll write a ticket to remove it soon.

To add on, I know a lot of people see the terminal as cruft/legacy from the mainframe days. But it is a funny thing to look at tons of people's IDE setup and see that the one _consistent_ thing between them all is that they have a terminal nearby. It makes sense, too, since programs run in the terminal and you can only abstract so much to developers. And like James said, this sets us up nicely to build for a future of coding agents running around. Feels like a unique insight, but I dunno. I guess time will tell.

A skilled surgeon is a great analogy! We actually instruct Codebuff to focus on making the most minimal edits, so that it does precisely what you want.

Sorry Will try an external keyboard next time!

Weird, thanks for flagging – we're just using a Youtube embed in an iframe but I'll take a look.

No worries if this isn't a good fit for you. You're welcome to try it out for free anytime if you change your mind!

FWIW I wasn't super excited when James first showed me the project. I had tried so many AI code editors before, but never found them to be _actually usable_. So when James asked me to try, I just thought I'd be humoring him. Once I gave it a real shot, I found Codebuff to be great because of its form factor and deep context awareness: CLI allows for portability and system integration that plugins or extensions really can't do. And when AI actually understands my codebase, I just get a lot more done.

Not trying to convince you to change your mind, just sharing that I was in your shoes not too long ago!

Haha yes, here's the story of why we rebranded: https://manifold.markets/JamesGrugett/what-will-we-rename-ma...

Thanks for sharing! haxton was asking about practical use cases, I'll link them here!