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
Keryx
AI research with verifiable sources and creator rewards
Keryx is an open-source research agent. Ask a question, set a budget, and follow BUY/SKIP/CACHE decisions. Inspect source excerpts, citations, article versions and payment receipts. Eligible, evidence-verified citations can reward creators in USDC on Arc mainnet. Free public references stay free. Use the web, MCP or API. Early access: gaps and incomplete answers are explicit. The video shows an earlier Arc-testnet build; screenshots show the current app.
Hi Product Hunt! I’m Tang, the maker of Keryx.
I’m building a research agent where you can inspect both the evidence and the money decisions. Give Keryx a question and a budget, then follow why it buys, skips or reuses a source. Results include source excerpts, article versions and receipts. Eligible citations that pass the evidence checks can reward creators in USDC on Arc.
You can start with a free web trial or connect your own agent through MCP or the API. Writers can prove ownership of their feed and choose how their work is offered.
This is early access. Keryx shows evidence gaps and incomplete answers, and the Windows Operator client remains an alpha. I’d love feedback from researchers, agent builders and independent writers: what evidence or payment details would make you trust a research agent?
Try it: https://keryx.cc
Source code: https://github.com/tang-vu/keryx
About Keryx on Product Hunt
“AI research with verifiable sources and creator rewards”
Keryx was submitted on Product Hunt and earned 8 upvotes and 1 comments, placing #81 on the daily leaderboard. Keryx is an open-source research agent. Ask a question, set a budget, and follow BUY/SKIP/CACHE decisions. Inspect source excerpts, citations, article versions and payment receipts. Eligible, evidence-verified citations can reward creators in USDC on Arc mainnet. Free public references stay free. Use the web, MCP or API. Early access: gaps and incomplete answers are explicit. The video shows an earlier Arc-testnet build; screenshots show the current app.
On the analytics side, Keryx competes within Productivity, Open Source, Artificial Intelligence and GitHub — topics that collectively have 1.3M followers on Product Hunt. The dashboard above tracks how Keryx performed against the three products that launched closest to it on the same day.
Who hunted Keryx?
Keryx was hunted by Tang Vu. 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 Keryx including community comment highlights and product details, visit the product overview.
Tang Vu