# langgptai/LangGPT

LangGPT: Empowering everyone to become a prompt expert! 🚀  📌 结构化提示词（Structured Prompt）提出者 📌 元提示词（Meta-Prompt）发起者   📌 最流行的提示词落地范式 | Language of GPT  The pioneering framework for structured & meta-prompt design 10,000+ ⭐ | Battle-tested by thousands of users worldwide  Created by 云中江树

Repository: https://github.com/langgptai/LangGPT
Canonical: https://ross.abutalabs.com/products/langgpt
Homepage: https://github.com/langgptai
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: prompt-engineering, chatgpt, deeplearning, framework, gpt-4, gpt3-prompts, langgpt, claude, doubao, gemini, meta-prompting, prompt, qwen, structured-prompts
Last push: 2026-07-16T14:03:09+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 35, longevity 86
- inputs: {"age_days": 1215, "days_push": 48, "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 12457, forks 942 (observed 2026-08-28T04:10:58.982672+00:00)

## What it is
LangGPT is a structured, reusable prompt design framework for large language models, offering template-based methodology with variables, commands, and conditional logic. It is the most widely adopted structured prompt paradigm in the Chinese AI community, backed by an arXiv paper and extensive documentation.

## Use cases
- write high-quality structured prompts for ChatGPT or Claude
- learn prompt engineering from scratch
- create reusable prompt templates for LLMs
- design meta-prompts that generate other prompts
- standardize prompt writing across a team
- improve GPT-4 output quality with structured instructions

## When to choose
- you want a battle-tested, widely adopted structured prompt methodology
- you need reusable, modular prompt templates rather than one-off prompts
- you want community resources and examples in Chinese and English

## When to avoid
- you need executable software or a runtime tool rather than a methodology and templates
- you prefer purely ad-hoc conversational prompting without structure
- you need a programmatic prompt library with API integrations

## Facets
- artifact type: framework
- maturity: active
- function: prompt-engineering, agent-framework, documentation
- domain: large-language-models, artificial-intelligence, tutorials
- platform: cross-platform
- tags: structured-prompts, meta-prompting, chatgpt, claude, prompt-templates, chinese-community

## Member repositories
- langgptai/LangGPT (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:58.982672+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 2026-08-29T17:14:02.513878+00:00, confidence not recorded.
  - readme: https://github.com/langgptai/LangGPT (fetched 2026-08-28T04:10:58.982672+00:00, sha d2a5feccc98a)
  - homepage: https://github.com/langgptai (fetched 2026-08-29T08:10:47.971509+00:00, sha 8e5becb4d3ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.