Your AI already drafts your X posts, but it has never seen how they performed. LinkIntel fixes that. Connect X once and it records how your recent posts do, every day. It also reads X's open-source ranking weights daily and links every change to its GitHub commit. Add one URL to Claude, ChatGPT, or your favorite agent harness and ask for a brief: your next draft starts from what actually worked for you
Hey Product Hunt, I'm Marcos, a solo founder in the UK.
I write most of my X drafts with Claude now. It kept telling me a post would do well, with total confidence, without ever having seen how a single one of my posts actually did. Every draft started from the model's general idea of "good".
So I built LinkIntel. It plugs into the assistant you already use (it's an MCP server, so it's one URL to add) and gives it three things: - Your own X results. Connect X once and it records how your recent original posts do, every day. - X's ranking weights. X publishes its ranking code on GitHub. LinkIntel re-reads it daily and flags every change, with the commit as the receipt. This week likes went up and the "not interested" penalty got heavier. - A brief, with sources. Ask "what should I post next?" and your assistant answers from your results and those weights, and shows what informed it.
I use it every day. When X changed those weights, LinkIntel caught it, my assistant drafted a post about it in my voice, and I published it.
Honest feedback over upvotes, please. I'd love to know: what would you want your assistant to know about your past posts before it writes the next one?
About LinkIntel on Product Hunt
“Post insights delivered direct to your AI”
LinkIntel launched on Product Hunt on October 24th, 2026 and earned 115 upvotes and 6 comments, placing #6 on the daily leaderboard. Your AI already drafts your X posts, but it has never seen how they performed. LinkIntel fixes that. Connect X once and it records how your recent posts do, every day. It also reads X's open-source ranking weights daily and links every change to its GitHub commit. Add one URL to Claude, ChatGPT, or your favorite agent harness and ask for a brief: your next draft starts from what actually worked for you
On the analytics side, LinkIntel competes within Twitter, Social Media and Developer Tools — topics that collectively have 636.3k followers on Product Hunt. The dashboard above tracks how LinkIntel performed against the three products that launched closest to it on the same day.
Who hunted LinkIntel?
LinkIntel was hunted by fmerian. 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 LinkIntel including community comment highlights and product details, visit the product overview.
fmerian
Hey Product Hunt, I'm Marcos, a solo founder in the UK.
I write most of my X drafts with Claude now. It kept telling me a post would do well, with total confidence, without ever having seen how a single one of my posts actually did. Every draft started from the model's general idea of "good".
So I built LinkIntel. It plugs into the assistant you already use (it's an MCP server, so it's one URL to add) and gives it three things:
- Your own X results. Connect X once and it records how your recent original posts do, every day.
- X's ranking weights. X publishes its ranking code on GitHub. LinkIntel re-reads it daily and flags every change, with the commit as the receipt. This week likes went up and the "not interested" penalty got heavier.
- A brief, with sources. Ask "what should I post next?" and your assistant answers from your results and those weights, and shows what informed it.
I use it every day. When X changed those weights, LinkIntel caught it, my assistant drafted a post about it in my voice, and I published it.
Honest feedback over upvotes, please. I'd love to know: what would you want your assistant to know about your past posts before it writes the next one?