A deterministic engine that finds continuity errors in fiction without using an LLM.
-
Updated
Mar 27, 2026 - Python
A deterministic engine that finds continuity errors in fiction without using an LLM.
Curriculum-aware RAG system that generates coherent multi-session educational content using a Sequential Dependency Graph for structured planning, retrieval, and pedagogical progression.
Generates 20,000+ word handbooks grounded in your own PDFs: plans sections with word budgets, then verifies each one for grounding, repetition and padding. Runs fully offline with BM25 and no API keys; provider-agnostic OpenAI-compatible LLM clients.
Orchestrated long-form fiction: a spec tree, a fact ledger, and a verifier that refuses to commit prose that broke its brief.
Add a description, image, and links to the long-form-generation topic page so that developers can more easily learn about it.
To associate your repository with the long-form-generation topic, visit your repo's landing page and select "manage topics."