# aiwaves-cn/RecurrentGPT

Official Code for Paper: RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

Repository: https://github.com/aiwaves-cn/RecurrentGPT
Canonical: https://ross.abutalabs.com/products/recurrentgpt
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2024-05-15T03:35:35+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 85
- inputs: {"age_days": 1199, "days_push": 840, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1001, forks 157 (observed 2026-09-03T02:15:08.901319+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: llm-inference, prompt-engineering, rag, nlp
- domain: large-language-models, artificial-intelligence
- platform: python, cli
- tags: long-text-generation, recurrent-llm, creative-writing, research-paper, openai, natural-language-processing

## Member repositories
- aiwaves-cn/RecurrentGPT (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:08.901319+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:16:04.890085+00:00, confidence not recorded.
  - readme: https://github.com/aiwaves-cn/RecurrentGPT (fetched 2026-09-03T02:15:08.901319+00:00, sha 7251ad3623f3)
- Data as of 2026-08-30T08:39:29.467469+00:00.