Show HN: Penmentor – Claude marks up your handwritten math like a teacher

A developer released Penmentor, an open-source Linux tool that sends handwritten math from the xournal++ note-taking app to a command-line AI agent — Claude Code, OpenAI Codex or Antigravity CLI — so the model marks the work on the page with colored-pen-style corrections, offers hints instead of answers, and generates interactive manim animations in the style of 3Blue1Brown. Penmentor runs on the user's existing AI subscription, with the model selected in Settings via prefixes such as `claude:opus`, `codex:gpt-5.6-terra` and `agy:gemini-4-argon-medium`, and requires Linux on X11 (best with i3) plus rofi, slop, xdotool and PyQt6. The tool is installed by cloning the GitHub repository and running `bin/penmentor --selftest`, and a small xournal++ plugin shares the whole current page rather than only what fits on screen.

A maths mentor at the tip of your pen. Press a key while you work by hand: Claude, Gemini or GPT marks your work on the screen like a teacher with coloured pens, gives you hints instead of answers, and shows the idea as a 3Blue1Brown-style animation. <sub Handwriting in xournal++ → one key → the slip is marked on the page → box the integral → an interactive manim animation. video https://github.com/AbdullahAlhariri/penmentor/blob/main/docs/demo.mp4 ; for a repeatable recording the pen is scripted and the model's answer is a fixed example. </sub I study calculus with a pen tablet in xournal++. I kept screenshotting my work into Claude and reading long answers back, when what I wanted was a teacher looking over my shoulder: circle the mistake, tick what's right, nudge me toward the next step, and show me why. penmentor is that, one key away, on my own Claude subscription. - Hints, not answers. A ladder from a nudge to naming the technique to a faint ghost of the next line: you do the thinking, which is what makes it stick. - Feedback on your own work. The first real mistake circled where you made it, correct lines ticked, later lines that inherit the mistake underlined. The marks stay while you keep writing; Esc clears them. - Practice that makes you recall. Questions on your key steps answer by typing or by writing , find-the-error drills, "which technique fits?". - See it. Box what you want to understand and get an interactive animation made with 3Blue1Brown's own manim https://github.com/3b1b/manim : drag the bounds, retype a value, watch Riemann sums close in. - Whole page aware. A small xournal++ plugin shares the page you are on, not just what fits on screen. penmentor runs on the AI command-line agent you already use, on that subscription. Pick the model in Settings ; its prefix says which agent answers: | Prefix | Agent | For example | |---|---|---| | claude: | Claude Code https://claude.com/claude-code | claude:opus , claude:sonnet , claude:haiku | | codex: | Codex https://github.com/openai/codex | codex:gpt-5.6-terra | | agy: | Antigravity CLI | agy:gemini-4-argon-medium , agy:gemini-3.8-flash-medium | Settings lists the agents you have installed. How each one is run and what it sees: the guide https://github.com/AbdullahAlhariri/penmentor/blob/main/docs/guide.md how-it-works-and-what-leaves-your-computer . git clone https://github.com/AbdullahAlhariri/penmentor ~/src/penmentor ~/src/penmentor/bin/penmentor --selftest Linux on X11 best with i3 , with one of those agents logged in claude , codex or agy , plus rofi , slop , xdotool and PyQt6. Bind bin/penmentor to a key example https://github.com/AbdullahAlhariri/penmentor/blob/main/contrib/i3.conf . Setup, keys and how it works: the guide https://github.com/AbdullahAlhariri/penmentor/blob/main/docs/guide.md .