NODEPROMPT
starsforks
How to install NODEPROMPT?
taewooopark/nodeprompt
$git clone https://github.com/TaewoooPark/NODEPROMPTSpatial Prompt Engineering through Interactive Concept Graphs
README.md
| 1 | # NodePrompt |
| 2 | |
| 3 | **Spatial Prompt Engineering through Interactive Concept Graphs** |
| 4 | |
| 5 | <p align="center"> |
| 6 | <img src="https://img.shields.io/github/license/TaewoooPark/NODEPROMPT?style=flat-square&labelColor=000000&color=333333" alt="License"> |
| 7 | <img src="https://img.shields.io/github/stars/TaewoooPark/NODEPROMPT?style=flat-square&logo=github&logoColor=white&labelColor=000000&color=333333" alt="GitHub stars"> |
| 8 | <img src="https://img.shields.io/github/last-commit/TaewoooPark/NODEPROMPT?style=flat-square&labelColor=000000&color=333333" alt="Last commit"> |
| 9 | <img src="https://img.shields.io/github/languages/top/TaewoooPark/NODEPROMPT?style=flat-square&labelColor=000000&color=333333" alt="Top language"> |
| 10 | |
| 11 | <img src="https://img.shields.io/badge/TypeScript-000000?style=flat-square&logo=typescript&logoColor=white&labelColor=000000" alt="TypeScript"> |
| 12 | <img src="https://img.shields.io/badge/React-000000?style=flat-square&logo=react&logoColor=white&labelColor=000000" alt="React"> |
| 13 | <img src="https://img.shields.io/badge/Three.js-000000?style=flat-square&logo=threedotjs&logoColor=white&labelColor=000000" alt="Three.js"> |
| 14 | <img src="https://img.shields.io/badge/Vite-000000?style=flat-square&logo=vite&logoColor=white&labelColor=000000" alt="Vite"> |
| 15 | |
| 16 | <img src="https://img.shields.io/badge/Claude-000000?style=flat-square&logo=anthropic&logoColor=white&labelColor=000000" alt="Anthropic Claude"> |
| 17 | <img src="https://img.shields.io/badge/GPT-000000?style=flat-square&logo=openai&logoColor=white&labelColor=000000" alt="OpenAI GPT"> |
| 18 | <img src="https://img.shields.io/badge/Gemini-000000?style=flat-square&logo=googlegemini&logoColor=white&labelColor=000000" alt="Google Gemini"> |
| 19 | <img src="https://img.shields.io/badge/Grok-000000?style=flat-square&logo=x&logoColor=white&labelColor=000000" alt="xAI Grok"> |
| 20 | <img src="https://img.shields.io/badge/DeepSeek-000000?style=flat-square&labelColor=000000&color=000000" alt="DeepSeek"> |
| 21 | <img src="https://img.shields.io/badge/Qwen-000000?style=flat-square&labelColor=000000&color=000000" alt="Alibaba Qwen"> |
| 22 | </p> |
| 23 | |
| 24 | NodePrompt decomposes prompts — text, images, or PDFs — into multi-dimensional concept graphs, renders them on a 3D sphere, and lets users spatially reorganize ideas before resynthesizing them into structured prompts for higher-quality AI responses. |
| 25 | |
| 26 | > *"Thinking is non-linear. Language is linear. The sphere bridges that gap."* |
| 27 | |
| 28 | [한국어 README](./README_KR.md) · [**taewoopark.com** — author site](https://taewoopark.com) |
| 29 | |
| 30 | <p align="center"> |
| 31 | <video src="https://github.com/user-attachments/assets/388508da-4304-456e-a41e-19b30b890bff" width="100%" autoplay loop muted playsinline></video> |
| 32 | </p> |
| 33 | |
| 34 | <p align="center"> |
| 35 | <img src="./public/screenshots/sphere.png" alt="NodePrompt Sphere Mode — 50+ labeled concept nodes distributed on a 3D sphere via Fibonacci lattice, connected by Bezier edges in Mark Lombardi black-and-white network aesthetic. A natural language prompt on the left is decomposed into a navigable spatial concept graph." width="100%"> |
| 36 | </p> |
| 37 | |
| 38 | |
| 39 | --- |
| 40 | |
| 41 | ## Why NodePrompt? |
| 42 | |
| 43 | Traditional prompt engineering is a black box: you type text, get a response, and iterate blindly. NodePrompt makes the *structure* of your prompt visible and editable. |
| 44 | |
| 45 | | Traditional Prompting | NodePrompt | |
| 46 | |---|---| |
| 47 | | Linear text in, linear text out | Prompt decomposed into a concept graph | |
| 48 | | Opaque reasoning | Visible node weights, types, and relationships | |
| 49 | | Manual iteration | Spatial editing: drag, reweight, reconnect | |
| 50 | | Single perspective | 6 conceptual dimensions extracted simultaneously | |
| 51 | |
| 52 | The core innovation is **Human-AI Co-Decomposition**: AI proposes a conceptual structure, humans reshape it spatially, then AI resynthesizes — a cyclic collaboration loop grounded in knowledge structure theory. |
| 53 | |
| 54 | --- |
| 55 | |
| 56 | ## Theoretical Foundations |
| 57 | |
| 58 | NodePrompt's design draws from established research in cognitive science, knowledge representation, and information visualization. |
| 59 | |
| 60 | ### Cognitive Architecture |
| 61 | |
| 62 | - **Rosch's Basi |
People who liked this also viewed
6 picksType
- tunellm chat in text filePromptsJul 2026
- snippetsSupercharge your Snippets in VS Code — Manage your code snippets & AI prompts without quitting your editor.PromptsJul 2026
- prompt-optimizerAn AI prompt optimizer for writing better prompts and getting better AI results.PromptsJul 2026
- chatgpt_system_promptA collection of GPT system prompts and various prompt injection/leaking knowledge.PromptsJul 2026
- prompt-masterA Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retentionPromptsJun 2026
- python-prompt-toolkitLibrary for building powerful interactive command line applications in PythonPromptsMay 2026
