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).
WeMD turns any web page — including WeChat Official Account articles — into clean Markdown, entirely in your browser. No server, no account, no telemetry. It shows estimated tokens saved vs. the raw HTML before you paste into an AI.
I built WeMD after one specific frustration: I kept pasting articles into AI chat, and one day I checked how much I was actually sending. A single WeChat article is 1,172,581 characters of HTML. The readable part is 3,766 tokens. I was paying to feed my AI inline styles, tracking scripts and QR-code cards.
So I made a browser extension that does the cleanup locally:
Why local, not a server-side fetcher? Because a server never sees the page you see: logged-in docs, paywalled articles, SPAs after hydration, personalized internal pages. In the browser, the DOM is already rendered and the session is yours.
Full disclosure:
• Token counts are an estimate (chars/4 heuristic), not real tokenization — it's for magnitude, not billing.
• Conversion needs your browser session, so a page you can't open can't be converted.
• 100% local — no backend, no account, no telemetry. Permissions are activeTab/scripting/contextMenus/clipboardWrite/downloads, used only on click.
Free tier: single page + selection, token panel, Send-to-AI.
Pro ($3.99/mo, $29/yr, $59 lifetime): batch conversion with image bundling, custom front-matter.
No comment highlights available yet. Please check back later!
About WeMD on Product Hunt
“Stop feeding HTML to your AI. Send Markdown.”
WeMD was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #158 on the daily leaderboard. WeMD turns any web page — including WeChat Official Account articles — into clean Markdown, entirely in your browser. No server, no account, no telemetry. It shows estimated tokens saved vs. the raw HTML before you paste into an AI.
WeMD was featured in Browser Extensions (5.5k followers), Productivity (665.7k followers) and Developer Tools (523.2k followers) on Product Hunt. Together, these topics include over 277.4k products, making this a competitive space to launch in.
Who hunted WeMD?
WeMD was hunted by Wing. 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 WeMD stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hey Product Hunt 👋
I built WeMD after one specific frustration: I kept pasting articles into AI chat, and one day I checked how much I was actually sending. A single WeChat article is 1,172,581 characters of HTML. The readable part is 3,766 tokens. I was paying to feed my AI inline styles, tracking scripts and QR-code cards.
So I made a browser extension that does the cleanup locally:
• Full-page or selection → clean Markdown (headings, lists, tables, code blocks)
• WeChat-specific extraction — deep article parsing, promo tails and hidden template nodes trimmed
• Shadow-DOM aware — content inside web components is captured too
• Token savings panel — see estimated tokens saved vs. the raw HTML before you paste
• Send to AI — one click to open your AI assistant with the Markdown ready
• Batch convert + image bundling (Pro) — merge all open tabs, rewrite image links to local files
Measured on real pages [chars/4 heuristic]:
• WeChat article: 1,172,581 chars → 3,766 tokens (−99.7%)
• Zhihu column: 76,338 → 817 (−99%)
• MSN long read: 14,310 → 815 (−94%)
• python.org docs: 13,245 → 746 (−95%)
Why local, not a server-side fetcher? Because a server never sees the page you see: logged-in docs, paywalled articles, SPAs after hydration, personalized internal pages. In the browser, the DOM is already rendered and the session is yours.
Full disclosure:
• Token counts are an estimate (chars/4 heuristic), not real tokenization — it's for magnitude, not billing.
• Conversion needs your browser session, so a page you can't open can't be converted.
• 100% local — no backend, no account, no telemetry. Permissions are activeTab/scripting/contextMenus/clipboardWrite/downloads, used only on click.
Free tier: single page + selection, token panel, Send-to-AI.
Pro ($3.99/mo, $29/yr, $59 lifetime): batch conversion with image bundling, custom front-matter.
Live on all three stores today (v0.4.7):
Firefox · Chrome · Edge — links on wemd.zyx.pink
Happy to answer anything 🙌