MCP server: Apple-keynote-style animated HTML lessons for self-study, with memory anchors, notebook pages and agent-made pictures
View on GitHub ↗The aurora as light on a stage for lessons: illuminating ideas in vibrant waves across the night.
An MCP server that lets AI coding agents (Google Antigravity, Claude Code, Cursor…) build self-study slides as beautiful as an Apple Keynote: big type, frosted glass, slowly drifting aurora backgrounds, spring animations, Magic Move, an exploded view like the old Mac product pages (the whole object → zoom in → its parts separate as you scroll), and interactive learning blocks: quizzes, flip cards, cloze, notebook pages, timed exercises and memory anchors (memory palace, picture anchors, analogies, mnemonics). Every lesson is one self-contained HTML file: open it in a browser and start learning.
It is built around one way of studying, theory → memory anchors → copy into a notebook → practice → review, and around courses of small lessons: a big subject (say, quantum computing) is split into short lessons, each with its own look, plus a course home page that tracks progress.
Current version: 0.8.0. Author: DuongNAD.
Aurora Slides pairs with sister project Polaris, the learner's AI course architect. Polaris creates the learner profile, conducts deep research with sources, designs roadmaps, schedules lessons, and exports course.json plus lesson outlines to /polaris/lessons/.outline.md. Aurora renders the interactive slides and records the learner's self-study progress into progress.jsonl. Polaris reads progress.jsonl via polarisprogresssync to populate the learner's error log ("Sổ lỗi") and plan spaced reviews.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/DuongNAD--aurora-slides-mcp.html)
ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
shinthink/blitzstrike⚡ Blitz Strike — a universal MCP penetration-testing toolbelt. Structured methodology: reconnaissance & attack-surface mapping, source-to-sink analysis, and live validation. 57 escalation chains, 130-
0xwilliamortiz/openclaude-improvedruns anywhere. uses anything
halofyai/halofyHalofy is the open access and governance layer for AI agents across your organization. Identity, policy, provenance, audit, and signed erasure.
CaptureGrubEnchant/SolidWorksSolidWorks MCP Server connects an AI assistant to a running SolidWorks instance. Sketch, extrude, fillet, export STEP/STL, generate macros.
arielshad/3d-asset-server3d assets api and mcp
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.