cjyyx/AI_Gen_Novel
基于大语言模型(LLM)和多智能体(Multi-Agent),探究AI写小说能力的边界
Implements a multi-agent architecture inspired by RecurrentGPT that decomposes novel writing into planning, drafting, and review phases—compressing long narratives into memory tokens and using iterative text generation to handle arbitrary lengths. Addresses LLM limitations in long-form coherence and originality through prompt optimization, agent collaboration, and incorporation of web fiction domain knowledge. Provides both a Gradio-based UI and CLI interface for generating serialized fiction, with extensible LLM backend support.
397 stars. No commits in the last 6 months.
Stars
397
Forks
81
Language
Python
License
MIT
Category
Last pushed
Sep 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/cjyyx/AI_Gen_Novel"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ElliotXie/CASSIA
CASSIA: A multiagent llm based single cell Annottaion framework
iblameandrew/local-deepthink
It takes a village to raise a child: Google DeepThink 🧠 but in LangGraph and free - an original...
bandirevanth/Jarvis
AI Assistant - Made using ElevenLabs, Livekit & LangChain
DavidLMS/aphra
An open-source translation agent designed to enhance the quality of text translations by...
AliKelDev/levkila-trade
An autonomous crypto-trading agent that leverages Large Language Models for decision-making,...