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

Sketchy

Sketchy creates in-chat, interactive, visual explanations

Sketchy turns AI explanations into interactive, hand-drawn diagrams. Map your app’s architecture, trace a request from button to database, and click any linked node to open its source file. Use Sketchy in Claude or set it up in Cursor via npm. Draw freehand on the canvas or export to Excalidraw to keep editing. The model sends a compact scene description, and Sketchy handles layout and rendering without spending model tokens on either. Free and open source.

Top comment

Hi Product Hunt, I'm David, a student from Germany.

I built Sketchy because I got tired of AI explaining everything in walls of text. Sketchy lets Claude answer with interactive, hand-drawn diagrams: hover for details, or click through a step-by-step mode.

How it works: LLMs are bad at coordinate math, which is why raw SVG from a model ends up with overlapping boxes. In Sketchy, Claude only outputs a compact JSON scene with nodes, edges, groups and steps. elkjs handles the layout and orthogonal edge routing, and rough.js renders it in a hand-drawn style. Follow-up edits keep existing nodes in place, even when back-edges are added, so you can compare versions of a diagram.

Benchmark: With Sonnet in Claude Code, Sketchy averaged 686 output tokens per answer vs 962 for plain text, about 29% fewer. Cost came out at $0.58 vs $0.61. The first diagram in a conversation costs slightly more.

Also included:

  • Repo diagrams where clicking a node opens the file in VS Code, Cursor or Zed (desktop extension / Claude Code)

  • Arduino/ESP32 code to circuit diagrams (~50 parts from wokwi-elements)

  • Photo labeling with a local Florence-2 model (small ~280 MB up to large ~3.1 GB)

  • Export to SVG/PNG

Free and open source (MIT), available as a Claude chat skill or as an MCP extension for Claude Desktop and Claude Code.

Feel free to try it out and leave your Feedback!

About Sketchy on Product Hunt

“Sketchy creates in-chat, interactive, visual explanations ”

Sketchy was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #367 on the daily leaderboard. Sketchy turns AI explanations into interactive, hand-drawn diagrams. Map your app’s architecture, trace a request from button to database, and click any linked node to open its source file. Use Sketchy in Claude or set it up in Cursor via npm. Draw freehand on the canvas or export to Excalidraw to keep editing. The model sends a compact scene description, and Sketchy handles layout and rendering without spending model tokens on either. Free and open source.

On the analytics side, Sketchy competes within Productivity, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.7M followers on Product Hunt. The dashboard above tracks how Sketchy performed against the three products that launched closest to it on the same day.

Who hunted Sketchy?

Sketchy was hunted by ddkbs. 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 Sketchy including community comment highlights and product details, visit the product overview.