Opyt turns the people and topics you already follow into a knowledge base. Point it at your X bookmarks, Substack subscriptions, blogs, GitHub repos or arXiv papers, and it pulls in their archives. It reads a topic through, writes its own follow-up questions, and keeps looking for new work that builds on what you've collected. Share what your knowledge base, keep exploring, and let your AI read it all. Free, MIT licensed, and your knowledge base can stay local.
I kept bookmarking posts on X, subscribing to Substacks, and saving papers I meant to read. Most of them stayed unread. I wanted to use that material where I actually work and learn: Claude.
So I built Opyt. It turns the sources you already follow and trust into a knowledge base and keeps adding to it as they publish. You can ask questions about all of it from Claude, Cursor, Codex, or any MCP-compatible client.
Here’s how I use it: - Catch up on AI. Ask what’s new and get an answer drawn from people you follow and trust, plus research and repos Opyt found in the background. - Check before building. Search repos, papers, and posts together. Find out whether someone already built your idea and what others learned trying it. - Think through career decisions. Explore which industry you might want to work in, drawing on what your sources see growing, slowing down, or changing and where they disagree. - Share with a friend. Give each other access to your knowledge bases. Search both with one question, see whose collection each result came from, and revoke access whenever you want.
No new app to open. Opyt is free and MIT licensed, and you can keep your knowledge base local. You pay for the AI tools you use and any OpenRouter usage.
How do you handle information that becomes obsolete as it accumulates over time?
My bookmarks are a pretty noisy signal of what I actually care about though - half of them are "read later" items I saved and never opened, or a thread I bookmarked to argue with rather than agree with. How does Opyt tell the difference between something I follow because it's core to my work versus something I just skimmed once, before it becomes part of my AI's context?
Bookmarks pile up faster than anything else I save, so the hard part is what comes back, not what goes in. What decides the ranking on a query?
I spend way too much time scrolling through LinkedIn and X, and I’ve always wanted something that could actually make use of all the posts I save. I used to use Mind just to save things and find them later, but Opyt feels like a much more useful use case. Instead of just storing all those posts, it can actually turn them into a knowledge base and help me keep up with what I’ve been saving in a much more digestible way.
“Your attention is the context your AI is missing”
Opyt launched on Product Hunt on September 17th, 2026 and earned 81 upvotes and 7 comments, placing #18 on the daily leaderboard. Opyt turns the people and topics you already follow into a knowledge base. Point it at your X bookmarks, Substack subscriptions, blogs, GitHub repos or arXiv papers, and it pulls in their archives. It reads a topic through, writes its own follow-up questions, and keeps looking for new work that builds on what you've collected. Share what your knowledge base, keep exploring, and let your AI read it all. Free, MIT licensed, and your knowledge base can stay local.
Opyt was featured in Open Source (68.9k followers), Twitter (24.3k followers), GitHub (41.4k followers) and Search (18.1k followers) on Product Hunt. Together, these topics include over 49.9k products, making this a competitive space to launch in.
Who hunted Opyt?
Opyt was hunted by David Maimon . 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 Opyt stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
David Maimon
Hey Product Hunt,
I kept bookmarking posts on X, subscribing to Substacks, and saving papers I meant to read. Most of them stayed unread. I wanted to use that material where I actually work and learn: Claude.
So I built Opyt. It turns the sources you already follow and trust into a knowledge base and keeps adding to it as they publish. You can ask questions about all of it from Claude, Cursor, Codex, or any MCP-compatible client.
Here’s how I use it:
- Catch up on AI. Ask what’s new and get an answer drawn from people you follow and trust, plus research and repos Opyt found in the background.
- Check before building. Search repos, papers, and posts together. Find out whether someone already built your idea and what others learned trying it.
- Think through career decisions. Explore which industry you might want to work in, drawing on what your sources see growing, slowing down, or changing and where they disagree.
- Share with a friend. Give each other access to your knowledge bases. Search both with one question, see whose collection each result came from, and revoke access whenever you want.
No new app to open. Opyt is free and MIT licensed, and you can keep your knowledge base local. You pay for the AI tools you use and any OpenRouter usage.
What would you use it for first?
Learn more: useopyt.com (https://useopyt.com)
David