[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75042":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":18,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":28,"discoverSource":29},75042,"nodepad","mskayyali\u002Fnodepad","mskayyali","A spatial research tool that explores using AI to augment thinking, not replace it.","http:\u002F\u002Fnodepad.space",null,"TypeScript",1043,161,9,15,0,2,6,27,19.63,"MIT License",false,"main",[],"2026-06-12 02:03:31","# nodepad\n\n**A design experiment in spatial, AI-augmented thinking.**\n\n[![Watch the intro](https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FnCLY7rHAjWE\u002Fmaxresdefault.jpg)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nCLY7rHAjWE)\n\n*[Watch the intro →](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nCLY7rHAjWE)*\n\n---\n\nMost AI tools are built around a chat interface: you ask, it answers, you ask again. The interaction is sequential, conversational, and optimised for producing output. nodepad is built around a different premise: that thinking is spatial and associative, and that AI is most useful when it works quietly in the background rather than at the centre of attention.\n\nYou add notes. The AI classifies them, finds connections between them, surfaces what you haven't said yet, and occasionally synthesises an emergent insight from the whole canvas. You stay in control of the space. The AI earns its place by being genuinely useful rather than prominent.\n\n---\n\n## How it works\n\nNotes are typed into the input bar and placed onto a spatial canvas. Each note is automatically classified into one of 14 types — claim, question, idea, task, entity, quote, reference, definition, opinion, reflection, narrative, comparison, thesis, general — and enriched with a short annotation that adds something the note doesn't already say.\n\nConnections between notes are inferred from content. When you hover a connection indicator, unrelated notes dim. When enough notes accumulate, a synthesis emerges — a single sentence that bridges the tensions across the canvas. You can solidify it into a thesis note or dismiss it.\n\nThree views: **tiling** (spatial BSP grid), **kanban** (grouped by type), **graph** (force-directed, centrality-radial).\n\n---\n\n## Setup\n\n**Requirements**: a desktop browser and an API key from one of the supported providers.\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fmskayyali\u002Fnodepad.git\ncd nodepad\nnpm install\nnpm run dev\n```\n\nOpen [localhost:3000](http:\u002F\u002Flocalhost:3000).\n\n**Add your API key**: click the menu icon (top-left) → Settings → choose your provider → paste your key. The key is stored in your browser's `localStorage` and goes directly to the AI provider — it never passes through any server.\n\n**Enable web grounding** (optional): toggle \"Web grounding\" in Settings to let the AI cite real sources for claims, questions, and references. Supported on OpenRouter `:online` models and OpenAI search-preview models.\n\n---\n\n## Providers & Models\n\nSelect provider and model from the sidebar Settings panel. Each provider remembers its key independently — switching providers and back restores your key.\n\n### OpenRouter *(default)*\nAccess to all major models through a single key. Create a free account at [openrouter.ai](https:\u002F\u002Fopenrouter.ai) — use the free-tier models below with no credits, or add credits for GPT-4o, Claude, and Gemini.\n\n| Model | Notes |\n|---|---|\n| `openai\u002Fgpt-4o` | Default. Strong annotation quality, web grounding. |\n| `anthropic\u002Fclaude-sonnet-4-5` | Strong reasoning, complex research. |\n| `google\u002Fgemini-2.5-pro` | Long context, web grounding. |\n| `deepseek\u002Fdeepseek-chat` | Fast, cost-effective. |\n| `mistralai\u002Fmistral-small-3.2` | Lightweight, fast. |\n\n**Free tier** — no credits required, ~200 req\u002Fday limit, Nvidia-hosted, no web grounding:\n\n| Model | Notes |\n|---|---|\n| `nvidia\u002Fnemotron-3-nano-30b-a3b:free` | Nemotron 30B — fast, reliable. |\n| `nvidia\u002Fnemotron-3-super-120b-a12b:free` | Nemotron 120B MoE — higher quality, same speed. |\n\n### OpenAI *(direct)*\nUse your OpenAI API key directly. Web grounding via search-preview models.\n\n| Model | Notes |\n|---|---|\n| `gpt-4o` | Strong structured output, web grounding. |\n| `gpt-4o-mini` | Fast, capable, web grounding. |\n| `gpt-4.1` | Latest GPT-4, improved instruction following. |\n| `o4-mini` | Fast reasoning model. |\n\n### Z.ai\nGLM models from Zhipu AI. Get a key at [z.ai](https:\u002F\u002Fz.ai\u002Fmanage-apikey\u002Fapikey-list).\n\n| Model | Notes |\n|---|---|\n| `glm-4.7` | Strong reasoning, 200K context. |\n| `glm-5` | Z.ai flagship model. |\n| `glm-5-turbo` | Fast, community-tested. |\n\n---\n\n## Keyboard shortcuts\n\n| | |\n|---|---|\n| `Enter` | Add note |\n| `⌘K` | Command palette (views, navigation, export) |\n| `⌘Z` | Undo |\n| `Escape` | Deselect \u002F close panels |\n\nDouble-click any note to edit. Click the type label to reclassify manually.\n\n---\n\n## Data\n\nEverything lives in your browser. No account, no server, no database.\n\n- Notes are persisted to `localStorage` under `nodepad-projects`\n- A silent rolling backup is written on every change to `nodepad-backup`\n- Export to `.md` or `.nodepad` (versioned JSON) via `⌘K`\n- Import `.nodepad` files via the sidebar\n\n---\n\n## Tech\n\nNext.js · React 19 · TypeScript · Tailwind CSS v4 · D3.js · Framer Motion\n\n---\n\n## Contributing\n\nPull requests are welcome. I go through them regularly. Some will be merged, others may stay open.\n\n---\n\nA design experiment by [Saleh Kayyali](http:\u002F\u002Fmskayyali.com).\n\n---\n\n## License\n\n[MIT](LICENSE)\n","nodepad 是一个旨在通过AI增强而非替代人类思维的空间研究工具。它允许用户在一个空间画布上添加笔记，AI会自动将这些笔记分类为14种类型之一，并基于内容推断笔记之间的关联性，从而帮助用户发现尚未表达的想法或生成新的见解。该工具提供了三种视图模式：平铺、看板和图表，以适应不同的工作方式。nodepad适合需要进行复杂思考与创意发散的场景，如学术研究、项目规划和个人知识管理等。采用TypeScript编写，支持多种AI模型提供者，包括OpenRouter（默认）和OpenAI等，用户可以通过简单的设置开始使用这一创新性的思维辅助工具。","2026-06-11 03:52:04","high_star"]