unitagain/WenShape

WenShape文枢(原NOVIX写作):深度上下文感知的智能体小说创作系统

55
/ 100
Established

Employs a multi-stage orchestration pipeline (Archivist → Context Engine → Writer → Editor) with dynamic fact tracking and token budget allocation (128K default) to maintain consistency across long-form narratives. Data is stored as git-native YAML/Markdown/JSONL, enabling version control and collaborative workflows. Integrates with nine LLM providers (OpenAI, Anthropic, DeepSeek, Qwen, etc.) with per-agent configurability, plus wiki scraping (Fandom, Wikipedia) for fanfiction asset extraction.

267 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 19 / 25

How are scores calculated?

Stars

267

Forks

44

Language

Python

License

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/unitagain/WenShape"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.