English | 中文

An open-source agentic curriculum engine that generates pedagogically grounded course content through narrative frameworks.

Unlike static AI course generators, Plot Ark applies evidence-based instructional design principles — Bloom's Taxonomy, Krashen's i+1 difficulty scaffolding, and Cognitive Load Theory — so the curriculum it generates is structured the way learning actually works.

Agentic pipeline — a Tavily research agent searches real academic sources first, then injects verified URLs into the generation prompt. No hallucinated citations.

Multi-provider AI — switch between OpenAI (GPT-4o-mini) and Google Gemini via a single env variable. Bring your own key.

syllabus upload — drop PDF/DOCX → auto-fill form fields + extract required readings

research agent&human in the loop — Tavily research agent → human source review → approve/reject

module adjuistment — drag-and-drop reorder, inline editing, all fields editable

Knowledge Graph — concept map, node detail, natural language query with node highlight

▶ Full demo video (Google Drive)

Most EdTech AI tools treat artificial intelligence as a threat to be monitored — detecting whether students used AI, flagging "inauthentic" work, enforcing originality.

Plot Ark takes the opposite position.

AI is a cognitive tool, not a threat. A student who uses AI to draft an answer, then understands it, refines it, and can explain it in their own words — that student has learned. Copy-paste without comprehension is a student deceiving themselves, not a system to be policed.

Plot Ark has no AI detection mechanism. It never will. The question it asks is not "did you use AI?" but "did learning happen?" — and it answers that through Bloom's Taxonomy alignment, i+1 difficulty progression, and xAPI learner behavior tracking.

The curriculum engine itself is built the same way: AI generates the structure, pedagogy constrains the output, and the instructor stays in the loop. The tool thinks; the human decides.

Anthropic's Economic Index (Jan 2026) found r = 0.925 between prompt sophistication and response sophistication — the deeper you engage it, the deeper it responds.

Course Generation Pipeline

RAG & Knowledge Graph Ingestion

Planned agentic loop:

xAPI behavior events → Curriculum Agent → Redis learner state → Narrative Engine → LMS 

Prerequisites: Docker, an OpenAI or Gemini API key, a Tavily API key (free tier at tavily.com)

git clone https://github.com/Schlaflied/Plot-Ark cd Plot-Ark cp .env.example .env # Set AI_PROVIDER=openai or AI_PROVIDER=gemini # Add the corresponding API key + TAVILY_API_KEY docker compose up --build

The knowledge graph feature lets you ingest your own course materials (PDFs, PPTXs, or DOCXs) and explore them as an interactive concept map.

1. Go to the Knowledge Graph tab
2. In the Upload Materials panel on the right, fill in:
   • Subject name (required) — e.g. "Organizational Behavior"
   • Course code (optional) — e.g. "ADMS 2400"
   • Year (required) — which year of study this course belongs to
3. Drop your PDF / PPTX / DOCX files into the dropzone
4. Click Build Graph — ingestion runs in the background (~$0.10–0.30 per 10 PDFs at gpt-4o-mini rates)
5. Once complete, the graph appears automatically under the correct year and course tab

plot-ark/ ├── docker-compose.yml ├── .env.example ├── docs/ │ ├── architecture.md │ ├── Syllabus Upload.gif ← Demo: syllabus import → form auto-fill │ ├── research agent&human in the loop.gif ← Demo: research agent + source review │ ├── module adjuistment.gif ← Demo: module editing + drag-and-drop │ └── Knowledge graph .gif ← Demo: year sidebar, course management, fullscreen, query ├── frontend/ ← React + TypeScript + Vite │ ├── Dockerfile │ ├── index.tsx ← Entry point │ ├── App.tsx ← Main UI (curriculum engine + student view) │ ├── components/ │ │ └── GraphViewer.tsx ← LightRAG knowledge graph viewer │ └── vite.config.ts ├── backend/ ← Flask │ ├── Dockerfile │ ├── app.py ← SSE endpoint, Bloom's mapping, graph API │ └── ingest.py ← LightRAG ingestion script (PDF + PPTX) └── data/ ├── materials/ ← Drop course PDFs/PPTXs here (gitignored) ├── lightrag_storage/ ← Business Law graph (gitignored, regenerate) └── lightrag_storage_call/ ← CALL graph (gitignored, regenerate) 

• Flask SSE streaming backend
• React frontend with module card navigation
• Docker Compose dev environment
• Bloom's Taxonomy course code mapping
• i+1 difficulty progression
• Inline module editing (all fields)
• Drag-and-drop module reordering
• IMS Common Cartridge + Markdown export
• Tavily agentic research pipeline — real academic sources before generation
• PostgreSQL history — persist, favorite, and delete curricula
• LMS-style module sidebar (D2L Brightspace-inspired layout)
• Multi-type resource pipeline — academic / video / news with type badges and estimated time
• Structure self-check with auto-retry — validates complexity progression and module count
• LightRAG knowledge graph — PDF/PPTX ingestion → interactive force-directed concept map
• Knowledge graph query — natural language Q&A against course material graph, Redis-cached
• Assignment Timeline + Due Date calculator
• Human-in-the-loop source review — approve/reject Tavily results before generation
• xAPI mini-LRS — statement ingestion, learner state, professor analytics panel (mock data)
• Syllabus import — PDF/DOCX → auto-fill form + extract required readings
• Course narrative — course-level story generated at skeleton phase, professor-editable
• Citation format selector — APA / MLA / Chicago across all exports
• PDF + DOCX export — client-side jsPDF and python-docx backend
• Multi-course management — dynamic course slots with add/delete/rename/drag-reorder
• My Courses dashboard — card grid with course history overview
• Knowledge Graph course management — year sidebar, course banner, dynamic subject tabs, fullscreen, course search
• Knowledge Graph ingestion panel — drag-and-drop material upload, always-visible right panel
• Redis learner state management
• Professor LTM — preference learning from edit history
• LTI 1.3 — push into Canvas / Moodle

GNU Affero General Public License v3.0 — see LICENSE

• Free for personal use, research, and open-source projects
• Modifications must be open-sourced under the same license
• Network deployment requires your product to also be open-source
• Commercial licensing — open a GitHub Issue

• 🌟 Awesome-AI-Agents — agentic EdTech curriculum engine

Architectural inspiration from Hive (YC-backed AI agent infrastructure) — the node pipeline, shared memory, and evolution loop patterns informed the agentic curriculum engine design.

Knowledge graph layer powered by LightRAG (HKUDS) — incremental knowledge graph construction and prerequisite inference across course materials.

Two-phase generation pipeline design inspired by OpenMAIC (Tsinghua University) — the outline-first, then expand pattern informed Plot Ark's curriculum skeleton generation approach.

Built with Claude (Anthropic) as AI pair programmer.

Special thanks to the two chief quality assurance officers who supervised every late-night coding session — Icy (冰糖, white) and 雪梨 (calico):