Most AI media tools want your data in the cloud. Invenio is built for your Mac. It gives your AI local access to your video and photo libraries. Type "man on a bike" – it finds the exact frame, understands the context, and lets you drag it directly into Premiere or Final Cut. No cloud, no tracking, 100% local via Apple Neural Engine. Works with TBs on external drives. Visual search and OCR are completely free.
Hey Product Hunt! 👋
I'm Igor, the maker of Invenio.
I’m the kind of person who has "External_Drive_1", "2", and "3" filled with years of raw footage and photos. Whenever I needed "that one shot of a sunset" or a specific slide from a recorded Zoom call, I’d spend hours scrubbing through timelines.
I loved the search power of Google Photos, but I didn't want to upload terabytes of my private life or professional work to the cloud just to make it searchable.
That’s when it clicked: My Mac already has a powerful Neural Engine. Why can't it just "watch" and index my videos for me, locally?
So I built Invenio. It handles the heavy lifting on-device, meaning your files never leave your machine.
What it does for you:
• Visual Search: Find moments by simply describing them (e.g., "dog playing on a beach").
• Speech Search: Search for any words spoken in the video to find the exact moment instantly.
• Pro Workflow: Once you find the shot, just drag and drop it straight into Premiere, Final Cut, or DaVinci.
Visual search and OCR are completely free and unlimited.
I’m an indie dev and I’d love to hear your honest thoughts! If you’d like to try the Pro features (Voice Search), let me know in the comments and I’ll send you a promo code for full access.
Let's make video search feel human again! 👇
Congrats on the launch, I like the concept of using local AI for data exploration.
Wondering if new photos are synced automatically to a Invenio folder or we have to manually trigger it.
Also it's worth to consider adding some memory moment + desktop notification.
I confirm. For creators, search is a huge hidden productivity problem, especially when years of footage are sitting across external drives. “Google Photos-level search, but private and on-device” is a very clear positioning.
What was the hardest part technically, indexing large video libraries locally or making the search results precise enough?
I would like to know if you process all videos to create metadata locally or with every search the apple neural engine goes through all the videos ?
About Invenio on Product Hunt
“Local AI search for Mac video & photo libraries”
Invenio launched on Product Hunt on May 20th, 2026 and earned 75 upvotes and 7 comments, placing #23 on the daily leaderboard. Most AI media tools want your data in the cloud. Invenio is built for your Mac. It gives your AI local access to your video and photo libraries. Type "man on a bike" – it finds the exact frame, understands the context, and lets you drag it directly into Premiere or Final Cut. No cloud, no tracking, 100% local via Apple Neural Engine. Works with TBs on external drives. Visual search and OCR are completely free.
Invenio was featured in Privacy (11.1k followers), Artificial Intelligence (469.1k followers) and Photo & Video (2k followers) on Product Hunt. Together, these topics include over 102.8k products, making this a competitive space to launch in.
Who hunted Invenio?
Invenio was hunted by Igor Yusupov. 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.
Want to see how Invenio stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Igor Yusupov