Show HN: Void, an open-source Cursor/GitHub Copilot alternative (github.com)

347 points by andrewpareles ↗ HN
Hey HN, I'm Andrew, one of the creators of Void. I made this open source version of Cursor where you can get all of Cursor's core features but in a fully-customizable IDE (ctrl+k, ctrl+L). We love Cursor but there are so many other features we want to build, like allowing AI to edit multiple files at once, or giving AI better understanding of your file system. Void is the open-source, fully customizable tool we've been wanting.

The hard part: we're building Void as a fork of vscode. The repo has great documentation for extensions, but going deeper gets pretty involved. All of the code is OOP-based, and they mount DOM nodes the old-school way (which is what React was supposed to solve..). So adding new UI features isn't exactly trivial. Microsoft also made its extension marketplace closed-source so we (and Cursor) have to hack our way through it. One thing we're excited about is refactoring and creating docs so that it's much easier for anyone to contribute.

The other benefit of open source is we don't need to hide how our prompts are built, so we can transfer the private API logic that Cursor has right onto your local machine. This lets you host a model on-prem and have your data stay completely private. It also means you can go directly to LLM providers (OpenAI, Anthropic) instead of going through us as a middleman.

There's still a lot to build, and full disclosure, we are very early stage. But we're super excited about building and have a working prototype that we're quickly adding features to.

Let us know if there's anything you want to see in a Cursor-style editor. Or feel free to shoot us a pull request. Cheers!

167 comments

[ 3.1 ms ] story [ 224 ms ] thread
Hi, thanks for sharing. A question: What is the advantage of this approach compared to the tool I'm using right now - continue.dev ?
Tried the get in touch link, but the Google form says I need permission to view it.
(comment deleted)
Should be fixed now!
I'm surprised no one in targeting Jetbrains IDEs as seriously as Cursor has targeted vscode.

I'd imagine Jetbrains users are much more willing to pay, and the non-AI intelligence Webstorm has baked in save me almost as much cognitive load as Cursor does if not more compared to base vscode.

I tried Continue but it wasn't very smooth at all.

Jetbrains isn't open source and this seems to be a fork of vscode, not an extension so there's a bit more control on what's being done here.

Edit : This is only my guess, I have no internal knowledge of Cursor.

Intellij community edition is open source, but not the enterprise version. However, CE is pretty feature rich with a ton of users and if you're targeting indie developers, most are on CE anyways. I'd say if you do Intellij, you have to be in for the long game to build up to enterprise, but its doable.
That's interesting actually, I didn't know they even had a community edition but as I am reading anyway it seem it supports only Android, Swing, and JavaFX. That's quite a limitation no?
Supermaven[1] has addons for vscode as well for jetbrains (and neovim). And it is so good that I quickly decided for their paid plan

[1] https://supermaven.com/

They have announced they are building an editor; so while I'm a subscriber, I'm not sure how long the plugins will last
they really did? where could I read about this.

I prefer to stay with addon

Edit: I see it, this is in their newest blog post

They announced it with their new round

https://x.com/SupermavenAI/status/1835743882971426837

Yeah, my first thought is the plugins are going away sooner or later.

I hope they use Jetbrains as a base instead of VS Code (or roll their own). I strongly prefer IdeaVim or over the one in VS Code. It's the main reason why I don't use Cursor.

Try out the Claude dev vscode extension. It's much better than Continue in my experience.
JetBrains + CoPilot integration is pretty good.
AFAIK jetbrains has an AI Assistant now, too. But I cannot say anything about how it works.
It was sub-par when I last tried it, like many things JetBrains have been doing these days.

I love their products, and I would be sad if they can't stay competitive, but it looks like they are taking all the wrong turns.

you can try https://firebender.com. Its specifically designed for android studio, but still works well for intellij. I use it every day to develop the plugin itself.
Thanks. I'm already using GitHub CoPilot, but will give this a try.

Honestly speaking I'm not a big fan of chat based assistants, which was one of my complaints about IntelliJ's own assistant. Auto-complete feels more natural, although I can see that the suggestions might be more accurate and to the point with the chat based ones.

we're working on this right now. Expect to see auto-complete, and cmd+K functionality this week!
It's close to useless.

I would know, I made the mistake of paying yearly.

I don't know why, but I somehow expected that...
I started paying for Sourcegraph's Cody AI because of how great the integration was in JetBrains IDEs!

Happy user for a few months now :)

We're targeting android studio - https://firebender.com. I imagine its because Java Swing is actually extremely painful to work with and learn. Most developers interested in AI and the experience overlap with Sun Microsystem's Java Swing is not very large.
There is Cody (https://sourcegraph.com/cody). But their "applying code" feature is worse than Cursor. They put import lines on the bottom of the file, for example. Cursor's "applying code" is superb. Too bad it cannot be used with another IDE.
This is cool! I'm a regular user of Cursor (I barely write any code now - just prompt and tab tab tab).

The thing that's really keeping me in Cursor (vs decamping for Zed) is NOT the Cmd K or the sidebar chat. It's actual Cursor's Tab autocomplete model. I've tried many other tab completion models and Cursor Tab blows them out of the water. Supermaven's new release is promising, however.

For the use-case you're solving for (issues with code-privacy), I think something like https://codeium.com/ does already allow for on-prem deployments with enterprise support. I'm trying to think of who would be served well by a fork of VSCode vs Continue.dev or something like a codeium VPS deployment.

Curious: what is your use case for cursor, i.e. what is the problem domain or complexity level (on a scale from boilerplate code to core architecture) that you typically work with? Also what plan are you on and is that enough for your needs?
Hi, we're working with an large typescript codebase and I develop fully fledged features with Cursor which involve non-trivial UI wiring up work. Decent amount of state management using React too.

It's definitely not boilerplate level code - but it also also stops well short of architecture level work. Here's a recent prompt of me trying to implement line-by-line diff generation: https://pastebin.com/WRJpNwqc

When I need to do architectural/design work, I do it in multiple passes, not generating any code, just lots detailed text with tons of feedback/back-and-forth with the model.

I'm on the pro plan but it's not enough for my needs - I run through the quota in 10-15 days. Then, I revert to using Sonnet 3.5 via API key.

Big fan of Codeium here. They're the only player who took vim/neovim users seriously from the start, and it's great to see people building extensions like monkoose/neocodeium. Their models or ux may not always be the best available, but their understanding of their target market and their product positioning is peak IMO, particularly the enterprise/on-prem options you mentioned. My money's on them long-term.
Yeah, I have not given enough time and did so yesterday; it suggests new parameters for example, so I only have to begin a "refactoring" and then tab tab... Vim guys are missing out.
Congrats on getting it this far! The fun is just beginning, but it does sound like you have an idea of what you're getting into. Here are some thoughts:

There are quite a few extensions and AI editors offering the snippet-like 'tab autocomplete', but Cursor are the only ones afaik who have nailed the full file no-look 'tab-tab-tab-tab autofix' workflow, with what I assume must be a combination of monaco/vscode hackery similar to what you're doing, and their own tuned model (i.e. not an off-the-shelf llm). Is this the piece you're going after when you say 'all of Cursor's core features', or are you primarily focused on something else?

On the topic of extensions, as an occasional user of Cursor I noticed that they've always been able to quite happily 'import' extensions you've already downloaded to a local VSCode profile, which makes sense, but they've occasionally struggled to use the same marketplace APIs for searching for extensions. I'm not sure what you're hoping for here, but I'd suggest you settle for that approach as a starting point. Also be conscious that you're dealing with Microsoft, so be mindful of things like their brand guidelines[0], and avoid telling the world that you're 'hacking away' at their APIs. These things may seem insignificant and it's true that they probably won't cause you a problem unless you're successful.

Lastly, assuming that you're hoping to recruit contributors (which I assume is some of the motivation behind this post): you really need to sanitise your Github workflow and your repo CI. Your commit history[1] currently seems to mostly consist of you updating your docs and committing straight to your main branch with no review process or checks, and the only commit I can see that does have any kind of check in place, your initial commit, has a failed monaco check that you seem to have subsequently just disabled. You'll need to tidy this up a _lot_ and establish a testing baseline if you want to successfully scale the project or attract the calibre of contributor you'll need to be successful.

Hope that helps, best of luck with the project!

[0]: https://code.visualstudio.com/brand [1]: https://github.com/voideditor/void/commits/main/

That is the only reason I use Cursor. The autocomplete is way too good. For refactors, it's just magic! I tried using VSCode after using Cursor for a whole month and Copilot is just straight trash in comparison.

I'd like to continue using Cursor but I'm don't want to have to buy Claude subscription twice (Cursor uses claude under the hood), and I prefer claude sonnet over chat-gpt.

for me very useful feature in cursor is 'apply' where it just merges ai generated code with your code and you just only confirm or reject - for this they also use custom ai and this feature doesn't work with bring in your own key and you need subscription.
Seems to be a dupe of another Show HN post posted by the same user 4 days ago https://news.ycombinator.com/item?id=41523197
launched twice? gotta launch as much as possible in this competitive landscape
If you're not shipping, you're slipping
And if you're slipping you can't dip in
We did a smaller launch a few days ago, but we've actually made a lot of changes to our github contributing page, website, logo since then (based on the feedback). Just trying to ship fast, haha.
I only just realised you're YC-backed. Makes sense, glhf
Doesn't sound like it warrants another post.
Given that this one is getting traction, I think it indeed warranted another post.
A practice that is considered perfectly cromulent!
My primary usage of cursor is cmd+L and cmd+K, I'll give it a shot. Also, makes sense to make an open source alternative. How do you plan on monetizing?
We plan on selling to enterprise companies. We know a lot of companies want to keep their repos private and so we offer them on-prem hosting options. Closed source tools can't really do this because they have to keep their prompt building algorithms behind a private API that they own.

This seems to work pretty well for Codeium, which offers its product free to consumers (at a loss), and is still able to make net profit from enterprise companies. At least that's the plan for now!

>We know a lot of companies want to keep their repos private and so we offer them on-prem hosting options.

Is there anything more than this?

Oh, I’m yet to find a good alternative to Cursor’s RAG-powered side chat. It helps me work with huge codebases so much. Tried Continue, but it’s very unstable, and doesn’t work as well. Would prefer a command line solution, vscode plugin is the next choice, having a separate editor is not ideal, but I’m glad there’s some competition.
Not sure if this is what you'd like, but I remember this repo from some time ago https://github.com/Storia-AI/sage

Storia-AI/sage: Chat with any codebase with 2 commands

Thanks for the suggestion! It needs some work to set up, and it looks like it only works on Github repos. Also, to work with non-local LLMs, you can only use Pinecone for vector storage. I might have misunderstood something, but I will check it out again later.
(comment deleted)
> Would prefer a command line solution

I haven't tried this myself so I apologize if it ends up being bad, but I've seen Aider [0] get linked a few times from people who wanted a CLI solution for AI code completion.

[0]: https://aider.chat/

Aider is really cool for small projects, but it builds a repo map instead of using RAG. That works on small codebases, but totally fails to be useful on large ones.
How large?

In use, treesitter-derived approach seems far effective than rag.

>5k source files. They don't fit into the context. I know I can limit what is sent, and I can attach files in the Aider chat myself. But this is not perfect for making an LLM answer questions about a codebase when I don't know much context beforehand. With Cursor, I can just do "@codebase How is a %feature% implemented?", and it's very quick and often helpful with a couple of follow-ups.
Aider is AI pair programming in your terminal.

Aider lets you pair program with LLMs, to edit code in your local git repository. Start a new project or work with an existing git repo. Aider works best with GPT-4o & Claude 3.5 Sonnet and can connect to almost any LLM.

https://aider.chat/

See LLM Leaderboards as well: https://aider.chat/docs/leaderboards/

Thanks! I use Aider with Claude 3.5 Sonnet on smaller projects sometimes, and it's really fun and helpful when it can put a whole repo map into the LLM's context.
As someone who has recently tried to refactor our app atop of VSCode (treating it like a platform), we got burned by the UI design decisions that are not straightforward to overcome, let alone maintain. The closed-source MS marketplace did not help either towards our OSS goals.

However, I found Theia (https://theia-ide.org) on HN (like a bunch of other cool things; this is one way I justify the time I spend/sink on this site) and find it a much better fit for our OSS goals (foundation owned, open-source marketplace) with full mod-ability while being compatible to VSCode extensions API (in theory). I recommend you look into it for your app.

Is Theia related to Eclipse (the traditional Java IDE)? Or is the reference to "eclipse" just an unfortunate naming collision?
They created it, but the code base is unrelated.
Theia is the Monaco editor from VS Code with a different ui
It's made by Eclipse Foundation which was created to host projects around Eclipse the IDE. Kind of like project under Apache brand, Apache foundation and Apache the HTTP server.
You can publish your extensions on OpenVSX fyi. A lot of projects have started doing that now. Not all, but a good amount. Glad you found Theia though.
Ah interesting! I'm building https://double.bot (ai assistant vscode extension) and someone asked about VSCodium but I didn't realize there's a open marketplace for that specifically.
Thanks for sharing! If Theia is built on top of monaco, I wonder if a form of one-click switch might work. The monaco editor is theoretically part of the vscode repo, while the "workbench" with settings/configs lives one layer up.
Good job at creating more competition, but sorry for being a little bit rude, most software forks die out, try to convince me using this instead of Continue + Claude-dev, which are open source extensions for the vanilla VSCode (or VSCodium).

>Microsoft also made its extension marketplace closed-source

Ehm, Open VSX Registry exists.

Are you using a local model with Continue?
I've tried running 3B LLAMA on my old machine and it was sluggish and kinda bad, but Claude 3.5 Sonnet works great. I will try the 70B model, should be good enough.
Yeah, I’ve found local models are completely useless for coding tasks whereas openai and Claude can at least do some refactors with guidance
I didn't have much success with ollama either. You really need a great accelerator for it to be useful enough. Codestral however is working out great so thanks for the tip.
Hey congrats on the release. I don't have much to add other than to ask for more context about this statement-

> allowing AI to edit multiple files at once

Cursor already modifies multiple files at the same time. I typically do this by pressing cmd+shift+I and in the left side of the window the required files will be shown as they're being modified.

Plus points if keeping the tool free for home/OSS users and then charge for corporate or on-premise deployments.

One critical question to the users:

Is Void able to understand the source code files from the project as a whole?

What I mean is being able to read the project, and then make suggestions based on the code that was written and propose new functions? For example, I would see it as fantastic to write unit tests where I'd say: "Please write a unit test that is verifying the functions on ABC.class" or "update the unit tests for ABC.class".

I know it is difficult for an LLM to create a valid result on the first try, but at least it does same me a lot of time creating a skeleton with most of the functions and samples already there. Most times just have to fine tune or fix a few parts but can say it amplifies my output speed by at least 10x to have that kind of functionality.

What is your impression? Can it read all source code files on the project?

Why is this a Show HN not a launch HN? Is it simply a concept and not yet fleshed out?

Hard sell to choose you especially as a full on editor replacement (as well as a copilot replacement) without a demo or even gifs.

Why are so many coding assistant forks? Is it fashion or is there a technical reason? Imagine Python support being a fork. Or live server.
Because it's hard to reimplement VSCode from scratch?
VSCode has plugins
They are making changes that cannot be done or are very difficult with vscode extensions
What might they be? API calls, read all files, write to files, side bar, UI interactions in editor. These are things I would imagine an extension can do. Continue.dev is an example.
Do you need to "own" the whole editor to do what you're doing? Just maintaining sync with upstream is a massive rod for your own back, and I don't see what you gain. As others have said, alternative registries exist, and installation instructions of standalone plugins are easier on users than downloading and installing a whole editor.

Can't you just do your own "Copilot" extension and plumb in an instance to ollama? Isn't that what Continue does? https://marketplace.visualstudio.com/items?itemName=Continue...

But then they wouldn’t be able to capture as much analytics.
This investment by YC in both Void and Continue.dev perfectly exemplifies the VC spray-and-pray approach by backing two nearly identical open-source VSCode plugins for AI-assisted coding.

They're simply throwing money at similar projects in the same space, hoping one will stick, without any special insight or reason why one should be more successful over another.

I’m interested; are you suggested this is a bad thing, or just highlighting something of interest?
Not a bad thing, but just a reflection that among some of these products there is nothing special when compared to rest of the bunch, there are very similar products (even backed by the same investor), and us users have no clear idea what is different between them, if anything, and why we should use one over another.

I guess similar theme can be seen in LLM/AI space in general, or previously in the streaming services, just throw as much money at the problem in the hope that your solution will stick, without any significant and clear differentiation.

> This investment by YC in both Void and Continue.dev

Oh there's a lot more than that.

Just the two that I have recently been checking out and, as many other commenters in this thread asked, what is the difference between the two? I guess investors know something we don't, or they are just throwing money at the wall...
This is VC operations by design since forever.

Heck, even centuries ago, they'd fund multiple ship crews to navigate the Earth, hoping one would find smth interesting.

It's the model that works in high-risk, high-reward endeavors.

double.bot also backed by YC
I think more competition in the "AI Editor" space is good, but I have to ask – why not make it a VSCode extension? I feel it'd be much more accessible.

Are there limitations in the extension APIs that make it hard to implement?

Because it's difficult to monetize extensions and justify a large VC valuation...

(Void is HN backed)

Are you HN backed when your Show HN gets over 200 votes?
The linked website says "Backed by Y Combinator" lol
Idk, continue is absolute trash at the moment. It manages to break my entire VScode environment, including vim hotkeys.
A lot of folks prefer JetBrains over VSC. For example my top choice for an AI Editor today is Zed.dev which lets you trivially setup to use a variety of key maps including JetBrains.

https://zed.dev/

Zed looks promising, I'm waiting on editorconfig support PR to drop
Zed is very fast but has a long way to go still.

ssh server is still in early stages, not even p2p yet.

The requirement for extensions to be built in rust only makes it harder to adopt.

When they these 2 things get solved and the editor remains fast, it might actually be very tempting to replace vscode with zed.

Vscode is fantastic but tends to become bloated quickly....

The tradeoffs are certainly there. I'm expecting it to be a viable switch in a year or two.
Agreed, it’s not perfect but VS code is a pretty rich ecosystem. Dealing with the drift between a fork and the core product — and missing features/broken extensions that’ll inevitably come with that isn’t really something I want to deal with in my work flow.

Cursor has a pretty polished experience, but I keep coming back to VS Code and using continue.dev, which is a lot rougher around the edges, because the UI works well enough.

Hey, great question - you're right, extensions are more accessible - the thing is, there is no great way to build the native UI we'd want using them. For example, displaying the before-and-after is vital for us, and doesn't feel natural in an extension.

Extensions like Codeium do the most naive thing possible by writing something like <<<<<<< DIFF >>>>>>>> in your file, literally breaking syntax highlighting. Others like Copilot are super buggy.

Right now Void is built on top of an extension, but we're also modifying and hooking into parts of the IDE to make a more native UX.

> Any LLM, Anywhere.

> Host your own models locally, or communicate directly with your favorites.

Looks fantastic, will happily try this!

It’s just been so long since going from ‘head to code’ has been the hard part for me. I’d imagine you have to be very unfamiliar for this to be useful.
But why does it have to be a VSCode fork? Couldn’t it be a VSCode plugin?
(comment deleted)
Genuine question: why don’t you started from VSCodium if the the VSCode is too much hassle to deal with?
Isn't VSCodium built from the same source code as VSCode? Excluding a few proprietary things Microsoft puts into the official binaries.
most exciting is that it will run locally and we don't have to use middleman and give up our juicy data. lol