This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Cardstream.ai
Card recognition for live streams
Point a camera at a trading card and identify it live. Open-source card recognition for live commerce and streaming shows – the kind of breaks and rips you see on Whatnot or Fanatics Live. Connect the Ximilar API or your own identification system, and it calls once per card, not once per frame.
Hi Product Hunt! We’re the team behind Ximilar’s trading card recognition API, and Cardstream.ai is our open-source tool for people who sell cards live.
On Whatnot, eBay Live and TikTok Shop, breakers open packs on camera and name every card by hand. Cardstream.ai watches the same video and names each card in about half a second: name, set, number and a confidence level, with price statistics if you want them.
The hard part was cost. Identification is a paid API call, and a pipeline that checks every frame at 15 fps would make 54,000 calls an hour. So most of the work went into a local engine that finds the card, waits until it stops moving and checks whether it’s the same card as before. Only a new card triggers a call, about 100 an hour. Everything else runs on your own computer with no GPU. It reads an OBS output, a webcam or an RTSP/RTMP/SRT feed, and never logs in to your marketplace accounts.
We made it open source (Apache-2.0), so you can run it on your own hardware or connect your own recogniser instead of ours. It’s in beta and supports 25 trading card games, including Pokémon, Magic: The Gathering, Yu-Gi-Oh!, One Piece and Lorcana.
If you stream card shows, we’d like to hear what it should do next.
About Cardstream.ai on Product Hunt
“Card recognition for live streams”
Cardstream.ai was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #375 on the daily leaderboard. Point a camera at a trading card and identify it live. Open-source card recognition for live commerce and streaming shows – the kind of breaks and rips you see on Whatnot or Fanatics Live. Connect the Ximilar API or your own identification system, and it calls once per card, not once per frame.
On the analytics side, Cardstream.ai competes within Card Games, Video Streaming, API and GitHub — topics that collectively have 155.8k followers on Product Hunt. The dashboard above tracks how Cardstream.ai performed against the three products that launched closest to it on the same day.
Who hunted Cardstream.ai?
Cardstream.ai was hunted by Zuzana Raidová. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Cardstream.ai including community comment highlights and product details, visit the product overview.
Zuzana Raidová