Launch HN: Cardboard (YC W26) – Agentic video editor (usecardboard.com)
71 points by sxmawl 4 hours ago
Hey HN - we're Saksham and Ishan, and we’re building Cardboard (https://www.usecardboard.com). It lets you go from raw footage to an edited video by describing what you want in natural language. There’s a demo video at https://www.usecardboard.com/share/fUN2i9ft8B46, and you can try the product out at https://demo.usecardboard.com (no login required!)
People sit on mountains of raw assets - product walkthroughs, customer interviews, travel videos, screen recordings, changelogs, etc. - that could become testimonials, ads, vlogs, launch videos, etc.
Instead they sit in cloud storage / hard drives because getting to a first cut takes hours of scrubbing through the raw footage manually, arranging clips in correct sequence, syncing music, exporting, uploading to a cloud storage to share, and then getting feedback on WhatsApp/iMessage/Slack, then re-doing the same thing again till everyone is happy.
We grew up together and have been friends for 15 years. Saksham creates content on socials with ~250K views/month and kept hitting the wall where editing took longer than creating. Ishan was producing launch videos for HackerRank's all-hands demo days and spent most of his time on cuts and sequencing rather than storytelling. We both felt that while tools like Premiere Pro and DaVinci are powerful, they have a steep learning curve and involve lots of manual labor.
So we built Cardboard. You tell it to "make a 60s recap from this raw footage" or "cut this into a 20s ad" or "beat-sync this to the music I just added" and it proposes a first draft on the timeline that you can refine further.
We built a custom hardware-accelerated renderer on WebCodecs / WebGL2, there’s no server-side rendering, no plugins, everything runs in your browser (client-side). Video understanding tasks go through a series of Cloud VLMs + traditional ML models, and we use third party foundational models for agent orchestration. We also give a dropdown for this to the end user.
We've shipped 13 releases since November (https://www.usecardboard.com/changelog). The editor handles multi-track timelines with keyframe animations, shot detection, beat sync via percussion detection, voiceover generation, voice cloning, background removal, multilingual captions that are spatially aware of subjects in frame, and Premiere Pro/DaVinci/FCP XML exports so you can move projects into your existing tools if you want.
Where we're headed next: real-time collaboration (video git) to avoid inefficient feedback loops, and eventually a prediction engine that learns your editing patterns and suggests the next low entropy actions - similar to how Cursor's tab completion works, but for timeline actions.
We believe that video creation tools today are stuck where developer tools were in the early 2000s: local-first, zero collaboration with really slow feedback loops.
Here are some videos that we made with Cardboard: - https://www.usecardboard.com/share/YYsstWeWE9KI - https://www.usecardboard.com/share/nyT9oj93sm1e - https://www.usecardboard.com/share/xK9mP2vR7nQ4
We would love to hear your thoughts/feedback.
We'll be in the comments all day :)
telesilla 2 minutes ago
Helpful for those who care less about the craft and more about a quick outcome. Werner Herzog said that he watches his footage a few times, takes extensive notes then edits based on his notes. That's how he crafts such extraordinary, once-in-a-lifetime stories. But for those who are working on commercial or home movies, why not use AI to build a narrative? It can be like throwing dice and the outcome could be OK. Maybe even good.
Regardless, having a tool that knows the content of your footage is a huge time saver. Good luck with the product.
moinism an hour ago
Wow! congrats on the launch guys. client-side rendering is incredible, really. I saw your product somewhere and have it as an open tab in my chrome for ~2 weeks :D
I also saw another YC company, Mosaic, doing something similar. But your approach of chat-based editing is a lot closer to what I'm building. Shameless plug: I'm also working on a chat-based media processor. https://chatoctopus.com
But you guys are way ahead! will be looking at you for inspiration.
sxmawl 38 minutes ago
mosaic's approach is also v fresh. curious about the flow after a user q/a with an asset in chatoctopus?
and ig it's time to revisit that chrome tab :)
michaelevensen an hour ago
Love this idea! I built something similar last year https://www.usecrossfade.com and know how difficult this is to get right - I'm rooting for you guys!
ishandeveloper 40 minutes ago
Thank you! You're right, there are so many subtle things to get right, appreciate the kind words. Crossfade's landing page looks slick btw!
michaelevensen 36 minutes ago
Thanks! Yeah, it can just quickly spiral into this massive product when you take video editing which has a base level of features you sort of expect and add on a whole new paradigm like AI-assisted. But really like your approach!
barefootford 2 hours ago
Really impressive work guys! It seems like YC has funded a few companies attacking this but I think you all might have the best approach so far. Behind the scenes is the agent just editing using text/annotated timelines? I feel like the move is probably text for roughcut/narrative, then a vlm for digesting the initial roughcut, then adding broll and fixing timing issues. Feel free to steal my FCP xml generator. https://github.com/barefootford/buttercut
sxmawl an hour ago
happy that you liked our approach! also, i think it's a better idea to just give agent these tools and let it figure out its course of actions than giving it a specific workflow to work on - it seems like the world keeps reminding us the bitter lesson [http://www.incompleteideas.net/IncIdeas/BitterLesson.html] more frequently these days
will definitely check the XML exports, ty :)
WaylonKenning an hour ago
Funnily, this was an issue for myself so I built an open source AI video editor - https://github.com/waylonkenning/aidirector
Cardboard looks really well polished, well done!
sxmawl an hour ago
damn that's really cool, you ship fast!
moralestapia 2 hours ago
This is amazing (I'll add you on LinkedIn).
I recently started making videos for a loved one that lives far away, I started using CapCut and this is the kind of thing I was thinking "I wish it did that".
I'll definitely try it out. Congrats!
sxmawl 2 hours ago
that's really cool!
lmk if i can help in any way :)
calebm 3 hours ago
This seems like a great idea. Tools like video editors (and CAD) often impose a big learning curve - there is a big differential between "I want to do X" and actually knowing all the right buttons to press to do X. Good luck.
sxmawl 3 hours ago
appreciate your support!
jimmis 2 hours ago
Excited to see AI integrations into more non-text-related applications (coding, spreadsheets, proofreading etc). As someone who only occasionally needs to edit videos for product / feature reels, I'd happily ask an AI to "sync the narration to the video, cut away irrelevant footage, and add transitions". The convenience of being able to automate simple, repeatable tasks in creative software via ai is something that gets overshadowed a lot by the agentic coding discussions. I can only imagine the nightmare it would be for a tool like Premier to integrate effective ai features, so new ai-in-mind tools really feel like a necessity.
Great website and good luck!
sxmawl an hour ago
you understood well what we are building. non-text domains certainly have additionally challenges and we're working on making it reliable without learning curve.
also, appreciate the kind words on the site — give Cardboard a spin next time you need a product reel!
joshribakoff an hour ago
Very cool idea. If your product is about video, please fix your video players. I cannot even seek on my touch screen.
ishandeveloper an hour ago
my bad, I didn't test it enough on touch devices. Just pushed a fix, appreciate you flagging it!
sxmawl an hour ago
ah, ty for notifying about the mobile player. on it!
rd 3 hours ago
Who do you think your target customer is? Curious to know if you think the money is in short form, traditional YouTube videos, or even movie studios one day.
Great website btw. The onboarding was very pleasing
sxmawl 2 hours ago
there's value in all the categories you mentioned — we're not focusing on feature filmmakers right now.
target customers usually fall under one of these - marketers / creators / founders
popalchemist 13 minutes ago
Impressive UI. I assume you must be doing some kind of RAG + audio/video transcription on all the media. What's RAG architecture did you go with?
RobotToaster 2 hours ago
The 10gb file size is going to be limiting for anyone shooting prores or raw.
sxmawl 2 hours ago
yeah, i agree. we're actively working on bumping that up. it was 5GB last week
for now, an intermediate solution is to splice and upload.
adboio an hour ago
LET'S GOOOOOOO excellent product friends
sxmawl 37 minutes ago
ty ty!
deklesen 2 hours ago
Nice demo experience!
sxmawl 2 hours ago
ty!
danieltk76 2 hours ago
We use Cardboard at Vulnetic and it is an incredible product. The founders are easily accessible, and it has definitely made it easier to film feature update videos. I can't recommend them enough.
sxmawl 2 hours ago
glad i'm able to help, i really enjoy working with you!
jhatemyjob an hour ago
> We built a custom hardware-accelerated renderer on WebCodecs / WebGL2, there’s no server-side rendering, no plugins, everything runs in your browser (client-side).
Aight imma head out. Holy moly.
sxmawl an hour ago
haha xD
TimCTRL 2 hours ago
$60...eh