aiwaves-cn/RecurrentGPT

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

999 stars · 158 forks observed · 2026-10-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

RecurrentGPT is a Python implementation of a paper-proposed framework that simulates LSTM-style recurrence using natural language and prompt engineering to generate arbitrarily long text with an LLM. It maintains long-term and short-term memory in text form and iteratively produces paragraphs with plans for the next section.

Use cases

• generate long-form stories or novels with an LLM
• write science fiction iteratively paragraph by paragraph
• simulate LSTM recurrence with natural language prompts
• build an interactive writing assistant
• create interactive fiction with long-term memory
• research long-context text generation without fine-tuning

When to choose

• you need to generate very long, coherent text beyond a single LLM context window
• you want a research-grade implementation of language-based recurrence for study or extension
• you want an interactive human-in-the-loop writing tool

When to avoid

• you need production-grade, actively maintained software
• you want fully automatic generation without human editing steps
• you cannot use OpenAI's API or prefer local models without adaptation

Facets

library · maturity maintenance

llm-inference prompt-engineering rag nlp large-language-models artificial-intelligence python cli long-text-generation recurrent-llm creative-writing research-paper openai natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="aiwaves-cn/RecurrentGPT")