LangGPT and DecryptPrompt
About LangGPT
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
Based on the README, here's a technical summary that goes deeper: --- Provides a hierarchical, markdown-based template system with standardized sections (Role, Profile, Goals, Skills, Rules, Workflow, Initialization) that enables reusable prompt composition similar to code modules, with support for variables, commands, and conditional logic. Includes automation tooling via OpenAI GPTs, Claude Code integration, and a skill installer for streamlined deployment. The framework is grounded in academic research on dialogue dynamics and LLM behavior patterns, addressing systematic prompt engineering through documented theoretical foundations rather than trial-and-error.
About DecryptPrompt
DSXiangLi/DecryptPrompt
总结Prompt&LLM论文，开源数据&模型，AIGC应用
Curates research papers and implementation guides across prompt engineering, instruction tuning, RLHF, and agentic systems, with 68+ technical blog posts covering evolution from basic prompting (GPT-3) through advanced topics like DSPy, GraphRAG, and reasoning scaling. Maintains organized resource collections spanning open-source models, inference/fine-tuning frameworks, SFT/RLHF datasets, and domain-specific AIGC applications with hands-on code examples for LLM agents, RAG systems, and tool integration via MCP protocols.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work