An agentic harness that turns long videos into clips
S-Roll is a fully local agentic harness for video understanding. Open a podcast, gameplay recording, interview, or talk and describe the moment you want. S-Roll finds the footage, creates clips, suggests highlights, tracks subjects, and provides an editor for trimming, reframing, captions, titles, and export. All AI processing runs on your Mac, so videos, transcripts, and chats stay there. Free on the Mac App Store with no watermark.
Hey Product Hunt, I’m Ritik. Today I’m introducing S-Roll, an agentic harness for video understanding that turns long videos into clips through natural-language prompts.
Long videos are full of valuable moments, but finding them still means scrubbing through timelines or uploading entire recordings to the cloud. I built S-Roll to replace that workflow with a conversation.
Open a video and describe what you are looking for, such as “Find the KO clip” or “Find where they discuss AI safety.” S-Roll understands the recording, finds the relevant moments, and creates clips for review. From there, it can track the subject, reframe the shot, generate captions, and prepare the final export.
The entire system runs locally on Apple silicon. Videos, transcripts, and chats stay on the user’s Mac.
S-Roll is the first step toward Saliency, an operating system for video understanding that will own both the models and the agentic harness around them.
S-Roll is available free on the Mac App Store with no watermarks. I would love feedback on what works, what does not, and which video workflows should come next.
About S-Roll on Product Hunt
“An agentic harness that turns long videos into clips”
S-Roll launched on Product Hunt on September 17th, 2026 and earned 74 upvotes and 6 comments, placing #21 on the daily leaderboard. S-Roll is a fully local agentic harness for video understanding. Open a podcast, gameplay recording, interview, or talk and describe the moment you want. S-Roll finds the footage, creates clips, suggests highlights, tracks subjects, and provides an editor for trimming, reframing, captions, titles, and export. All AI processing runs on your Mac, so videos, transcripts, and chats stay there. Free on the Mac App Store with no watermark.
On the analytics side, S-Roll competes within iOS, Artificial Intelligence and Video — topics that collectively have 591.9k followers on Product Hunt. The dashboard above tracks how S-Roll performed against the three products that launched closest to it on the same day.
Who hunted S-Roll?
S-Roll was hunted by Ritik Bompilwar. 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 S-Roll including community comment highlights and product details, visit the product overview.
Ritik Bompilwar