{"version":1,"scope":"full","truncated":false,"id":"editorial-compare-cardloom","url":"https://wenbu.app/compare/cardloom/","locale":"zh","revision":"6fa53d4e1132f17e496ef12dbc984d193d841b3d46b161bd1546ae267754b784","updated":"2026-11-13T13:22:22.672Z","content":"# 问卜与 Cardloom：网页抽牌、本地手记与可选账号保存怎么选？\n\n按“抽牌—保留原始结果—导出或保存”的实际任务，比较问卜与 Cardloom 的公开说明：网页抽牌、本地手记、导出与账号选项。含一个假设的三张牌记录案例，并说明设备更换后的恢复未经验证。\n\nUpdated: 2026-10-30 · Wenbu AI-assisted editorial\n\n先看你的任务终点。若你只想在浏览器里抽一次牌、写几句自己的话、把记录留在本机并随时导出，问卜与 Cardloom 的公开页面都覆盖了这条路径：Cardloom 写明免费、无需账号、手记留在本浏览器，并提示换设备或清除浏览器数据前先导出；问卜的免费页列出 78 张塔罗抽牌、本地手记与 JSON 导出，且当前无需付款或注册。若你希望抽牌之外还能把同一套计算交给自己的 Agent，问卜公开了 MCP、CLI 与 REST 接口，Cardloom 的页面则描述可选的 AI 解读，每天最多三次。两者都没有在公开摘录中给出设备更换后的恢复保证，因此不要把“有导出”理解成“换机后一定找得回”。选择依据应是：你更看重可导出的本地记录，还是更看重可编程的接口与多工具计算。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/) · [Wenbu · agent integrations](https://wenbu.app/agents/) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n- 先确定终点：只要本地记录与导出，两者都覆盖；需要可编程接口时，问卜的公开文档更完整。\n\n- Cardloom 明确提示换设备或清除浏览器数据前先导出；问卜也提供 JSON 导出，但两者都未公开设备更换后的恢复保证。\n\n- 抽牌是随机过程，重复提问不会按需复现同一组牌；记录的价值在于保留当时的结果与你的笔记。\n\n## 从抽牌到换设备的决策流程\n\n1. **1. 抽牌并保留原始结果** — 在网页上选择一个牌阵并翻牌；问卜的方法页说明抽牌为随机过程，页面保留原始结果，不要为了更好看而重抽。\n\n2. **2. 写下问题与笔记** — Cardloom 把笔记列为可选，问卜也提供本地手记；记录问题、牌位与当时的想法，便于日后回看。\n\n3. **3. 导出本地副本** — Cardloom 提示换设备或清除浏览器数据前先导出；问卜免费页列出 JSON 导出。导出后应自己打开文件确认内容。\n\n4. **4. 换设备时自行搬运** — 两份公开摘录都未说明设备更换后的恢复流程或成功保证，因此把导出文件当作需要自己保管的副本，而不是自动同步。\n\n该流程把抽牌、留底、导出、换设备拆成可检查的步骤，并标出公开说明未覆盖的环节。它描述的是操作顺序，不是任何一方的存储保证。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## 先定义任务：抽牌、留底、再决定去向\n\n把选择拆成三步会更清楚：先抽一个牌阵，再把原始结果连同问题与笔记保存下来，最后决定是导出成本地副本，还是交给账号或外部工具。Cardloom 的公开页面把这条路径写得很直白：选择牌阵、翻牌、写可选笔记，然后保存到我的手记，并说明手记留在本浏览器、换设备或清除浏览器数据前应先导出。问卜的免费页同样列出 78 张塔罗抽牌、本地手记与 JSON 导出，且当前无需付款或注册。\n\n差别在于这条路径之外的延伸。问卜的公开文档还描述了 MCP 的 draw_tarot 工具，输入为 1 或 3 张、是否逆位，从完整牌组不放回抽取；CLI 与 REST 也以 JSON 返回结果。Cardloom 的页面则描述可选的 AI 解读，写明每天最多三次，并说明只有你选择提交的问题、牌与笔记才会送给模型。两者都适合抽完就记，但如果你想把结果交给自己的程序或 Agent，问卜公开的接口说明更具体。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/) · [Wenbu · agent integrations](https://wenbu.app/agents/) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## 本地手记与导出：两者都强调先留副本\n\nCardloom 对手记位置的表述很明确：手记留在本浏览器，导出副本是为了留个安全备份或带到另一台设备。这句话同时说明了两件事：默认存储是本地的，以及跨设备需要你自己搬运文件。问卜的免费页把本地手记与 JSON 导出并列为免费功能，并说明 AI 额度用完后仍可抽牌、保存手记和导出结果。就公开文字而言，两者都把导出当作读者自己的动作，而不是自动同步。\n\n需要保留的不确定性是：两份公开摘录都没有描述导出文件的字段结构、导入后的校验方式，也没有给出设备更换后恢复成功的保证。因此能导出只证明存在一个导出入口，不证明换机后一定能完整还原。若记录对你重要，稳妥做法是导出后自己打开文件确认内容，并保留一份与浏览器无关的副本；这是操作建议，不是任何一方公开承诺的存储保证。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/)\n\n## 账号、AI 与接口：按需选择，不比较谁更强\n\nCardloom 的页面写明阅读、牌义、课程与本地手记免费，没有结账或订阅；AI 模型解读限制为每浏览器每天三次。问卜的免费页则说明浏览器访客与登录账号每天最多 5 次工具页 AI 解读、12 回合 Agent 对话，按上海时间零点重置，登录会归并当天试用用量而不会重新赠送。这些是各自公开的额度说明，不能据此推断对方的定价或未公开的限制。\n\n在接口方面，问卜公开了 MCP 的七种工具、CLI 与 REST 的 JSON 返回，并说明计算请求不需要问卜账户，只有选择内置 AI 时才把所选内容进一步交给模型。Cardloom 的公开摘录没有描述 API 或导出格式；但这只说明该页面没有覆盖这些内容，不能据此断定 Cardloom 不具备相关能力。比较时应把页面没写与产品没有分开。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/) · [Wenbu · agent integrations](https://wenbu.app/agents/)\n\n## 随机性与记录：为什么重复提问不等于复现\n\n问卜的方法页说明，塔罗从 78 张牌中等概率抽取 1 张或 3 张，同一次抽取不会重复；开启逆位时每张牌独立有 50% 概率呈逆位，三张牌的位置是当下、牵引、下一步，用于组织思考而非必然顺序。这意味着抽牌结果由随机过程产生，你重复同一个问题，并不会按需得到同一组牌；偶尔重复只是巧合。\n\n因此记录的重点不是验证牌准不准，而是保留当时抽到了什么、你写了什么、后来发生了什么。Cardloom 的日签说明建议保留一句笔记，到晚上再看看自己注意到了什么；它没有给出“把提示当作可选小实验”或“区分牌面联想与实际发生”的规则。问卜的日签页才明确建议把提示当成可选择的小实验，并分清牌面让我想到的和实际发生的。问卜的方法页要求把传统含义、AI 推断与现实情况分开看待；Cardloom 的页面把牌义说明称为现代反思提示，但没有陈述同样的三层规则。\n\n[Wenbu · calculation conventions](https://wenbu.app/methodology/) · [Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · daily card](https://wenbu.app/daily/)\n\n## 按任务对照两份公开说明\n\n| 任务环节 | Cardloom 公开说明 | 问卜公开说明 | 未验证或未覆盖 |\n| --- | --- | --- | --- |\n| 网页抽牌 | 选择牌阵、翻牌，含每日一张、三张牌与自定义牌阵 | 78 张塔罗抽牌，1 或 3 张，完整牌组不放回 | 两者的抽牌界面细节未逐一测试 |\n| 本地手记 | 手记留在本浏览器，笔记可选 | 本地手记，免费页列为免费功能 | 导出文件的字段结构未在摘录中说明 |\n| 导出 | 可导出与导入手记，提示换设备前先导出 | JSON 导出 | 导入后的校验与设备更换恢复未验证 |\n| 账号与 AI | 免费、无需账号；可选 AI 每天最多三次 | 免费无需注册；AI 额度按访客与账号分别说明 | 账号保存与同步状态未做实测 |\n| 可编程接口 | 公开摘录未描述 | MCP、CLI、REST 返回 JSON | Cardloom 是否有接口未由该页面证明 |\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/) · [Wenbu · agent integrations](https://wenbu.app/agents/) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## 假设案例：一次三张牌记录如何走完导出与换设备\n\n以下为虚构示例，用于演示记录流程，不代表任何真实抽牌结果，也不是计算出的命盘。假设读者小林在浏览器里就是否接受一个新项目抽三张牌，位置为当下、牵引、下一步，并写下笔记。\n\n1. 第一步：抽牌。小林在网页上选择三张牌阵，翻牌后看到三张牌与正逆位状态。按问卜方法页的说明，这是一次随机抽取，同一次抽取不重复；她不为更顺而重抽。\n\n2. 第二步：留底。她把问题、三张牌的名称与正逆位、以及一句自己的观察写进手记。Cardloom 的页面把笔记列为可选，并说明手记留在本浏览器；问卜也提供本地手记。\n\n3. 第三步：导出。她使用导出功能生成一份本地副本，并立刻打开文件，确认三张牌、位置与笔记都在。Cardloom 提示换设备或清除浏览器数据前先导出；问卜免费页列出 JSON 导出。\n\n4. 第四步：换设备。她换了一台电脑，尝试把副本带过去。两份公开摘录都没有描述导入后的校验或恢复保证，因此这一步的结果属于未测试范围；她只能确认自己手里有一份可读的副本。\n\n5. 第五步：回看。几周后她对照笔记与实际进展，区分牌面让我想到的和实际发生的，不把任何一方的解释当作预测结论。\n\n这个案例能教的具体一点是：记录的价值来自原始牌面、位置、自己的笔记和一份自己确认过的副本，而不是来自重复抽牌或某个准确率说法。设备更换后能否完整恢复，公开说明没有给出保证，应如实标为未验证。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## FAQ\n\n### 两者都免费、都无需账号，那还比什么？\n\n比的是任务终点。若你只要网页抽牌、本地手记与导出，两者公开说明都覆盖；若你还想把抽牌结果交给自己的程序或 Agent，问卜公开了 MCP、CLI 与 REST 的 JSON 返回，Cardloom 的公开摘录没有描述接口。反过来，Cardloom 页面明确写了可选 AI 解读每天最多三次，这也是它公开说明的一部分。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/) · [Wenbu · agent integrations](https://wenbu.app/agents/)\n\n### 导出之后，换设备一定能恢复吗？\n\n不能这样承诺。Cardloom 提示换设备或清除浏览器数据前先导出，问卜列出 JSON 导出，但两份公开摘录都没有描述导入校验或设备更换后的恢复保证。稳妥做法是导出后自己打开文件确认内容，并保留一份与浏览器无关的副本；设备更换后的恢复属于未测试范围。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/)\n\n### 重复问同一个问题，会抽到同一组牌吗？\n\n不会按需复现。问卜方法页说明塔罗由程序随机抽取，同一次抽取不重复；重复提问是新的随机过程，偶尔重复只是巧合。记录应保留当时抽到的牌与笔记，而不是靠重抽去凑一个想要的结果。\n\n[Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n### Cardloom 页面没写 API，是不是就没有？\n\n不能这样推断。公开摘录只覆盖该页面写到的内容，没有描述 API 或导出格式，只说明该页面未涉及这些主题，不等于产品不具备相关能力。比较时应把页面没写和产品没有分开，并以各自公开说明为准。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · agent integrations](https://wenbu.app/agents/)\n\n## Glossary\n\n- **本地手记**: 保存在当前浏览器中的阅读记录，通常需要读者自己导出副本才能在换设备或清除数据后保留。 [Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/)\n\n- **不放回抽取**: 从完整牌组中抽牌，同一次抽取中每张牌最多出现一次；问卜的 draw_tarot 工具按此规则抽取 1 或 3 张。 [Wenbu · agent integrations](https://wenbu.app/agents/) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n- **逆位**: 牌面呈倒置状态的一种读法选项；问卜说明开启逆位时每张牌独立有 50% 概率呈逆位。 [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n- **导出副本**: 由读者主动生成、可保存在浏览器之外的文件；存在导出入口不等于承诺换设备后自动恢复。 [Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · current free access](https://wenbu.app/free/)\n\n## Evidence notes\n\n- Cardloom 的公开页面写明阅读与本地手记免费、无需账号，并提示换设备前先导出。 — “Free readings · No account” (fact); [Cardloom · official readings and local journal](https://cardloom.site/)\n\n- 问卜免费页列出 78 张塔罗抽牌、本地手记与 JSON 导出，当前无需付款或注册。 — “78 张塔罗抽牌、本地手记、JSON 导出” (fact); [Wenbu · current free access](https://wenbu.app/free/)\n\n- 问卜的塔罗抽牌由程序随机抽取，页面保留原始结果，计算可复现不代表解释已被科学验证。 — “塔罗和在线起卦由程序随机抽取。页面会保留原始结果。” (editorial); [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## Sources\n\n- [Cardloom · official readings and local journal](https://cardloom.site/) — Vendor statements about browser draws, physical-deck logging, local journal export and optional AI; no account, storage or security audit; fetched 2026-10-30T07:00:36.246Z; complete response\n\n- [Wenbu · current free access](https://wenbu.app/free/) — First-party access and quota documentation; fetched 2026-10-30T07:00:36.222Z; complete response\n\n- [Wenbu · agent integrations](https://wenbu.app/agents/) — Current first-party product documentation; fetched 2026-10-30T07:00:36.235Z; complete response\n\n- [Wenbu · calculation conventions](https://wenbu.app/methodology/) — First-party implementation; not evidence of predictive accuracy; fetched 2026-10-30T07:00:36.212Z; complete response\n\n- [Wenbu · daily card](https://wenbu.app/daily/) — Current first-party product UI; not a personal forecast; fetched 2026-10-30T07:00:36.220Z; complete response\n\n- [Wenbu · versioned public capabilities](https://wenbu.app/capabilities.json) — First-party current tool, convention and privacy contract; not external endorsement or predictive validation; fetched 2026-10-30T07:00:36.222Z; complete response\n\n[先抽一次三张牌，写下笔记并导出一份副本](https://wenbu.app/tarot/)\n\n# 看魔术师的牌面时，选 Cardloom 还是问卜？\n\n用两份公开图鉴对照同一张魔术师。查经典韦特–史密斯画面时找 Cardloom，想练习对照不同画法时再翻问卜图鉴。\n\nUpdated: 2026-11-13 · Wenbu AI-assisted editorial\n\n教材要你找魔术师头顶的无限符号时，先看 Cardloom 的牌义页。它把这幅图标为 1909 年韦特–史密斯原画，人物头顶可见黑色横置八字。问卜图鉴的同一位置画了带放射线的金色圆盘。把两张图并排看，还能核对共有的举手姿势和桌面道具。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n- 先确认教材引用的是哪套牌，再查它提到的细节。\n\n- 先看人物头顶，再看举起的手和桌面。抄下一个保留的细节和一个变化。\n\n- 记录图鉴名称、牌名和核对日期，方便日后找回同一幅画。\n\n## 给一张牌做两栏观察\n\n1. **查经典牌面** — 在 Cardloom 的 Card meanings 打开 The Magician，先看人物头顶。\n\n2. **打开重绘版** — 在问卜图鉴打开魔术师，看同一块位置和举起的手。\n\n3. **留两条记录** — 记一个共同细节和一个不同细节，注明来源图鉴和日期。\n\n用牌名找到同一张牌，再按固定顺序看头顶、手势和桌面。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · daily card](https://wenbu.app/daily/)\n\n## 从教材提到的物件出发\n\n如果教材在讲帕梅拉·科尔曼·史密斯画的魔术师，从 Cardloom 首页的 Card meanings 进入，打开 The Magician。该页把图标为 1909 年原画。黄底上能看到人物头顶的黑色无限符号和手里举起的白色杖。\n\n在问卜塔罗工具页点「翻阅 78 张牌图鉴」，找到魔术师并打开图面。问卜把这套画标为以传统意象重新绘制的原创 AI 插画。这一版人物头顶是放射光芒的金色圆盘，抬起的手里握着带叶子的枝条。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## 给两张图各记一条可以核对的描述\n\n从人物头顶移到桌面，两幅画上都能找到杯、剑和带五角星的圆盘。如果教程把某件道具叫作「星币」，可以先记下图上的形状。下一位读者凭形状和位置就能找到同一件东西。\n\n两幅图和图鉴入口均于 2026 年 11 月 13 日核对。读特定教材时，选教材所指的版本。练习比较画法时，打开两页，在笔记里写明图鉴名称。牌义提示可以另写一行。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · daily card](https://wenbu.app/daily/)\n\n## 两张魔术师图的观察位置\n\n| 观察位置 | Cardloom | 问卜 |\n| --- | --- | --- |\n| 图鉴的版本标识 | 牌义页标为 1909 年韦特–史密斯原画 | 图鉴标为根据传统意象重绘的原创 AI 插画 |\n| 人物头顶 | 黑色横置八字 | 有光芒的金色圆盘 |\n| 举起的手 | 白色杖 | 带叶子的枝条 |\n| 桌面上都能找到的物件 | 杯、剑、带五角星的圆盘 | 杯、剑、带五角星的圆盘 |\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## 练习查教材里提到的无限符号\n\n假设一段入门教材请你在魔术师头顶找无限符号。这里用两张已核对的公开插图演示如何定位，不需要抽牌。\n\n1. 在 Cardloom 打开 Card meanings，选 The Magician。把位置记为人物头顶，形状记为黑色横置八字。\n\n2. 在问卜塔罗页打开牌图鉴，选魔术师。查看同一位置，把形状记为金色圆盘与放射线。\n\n3. 在两张图上各找一次杯或剑，给这件共同道具单独留一行。\n\n4. 在笔记里把无限符号归到 Cardloom 展示的版本，给问卜的金色圆盘单留一行。回看教材时，你可以直接找到它描述的那幅图。\n\n核对答案是 Cardloom 图有教材描述的符号，问卜图的同一位置用了金色圆盘。举手动作和若干桌面道具可以作为跨版本的比对线索。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## FAQ\n\n### 图上找不到教材说的符号，要回到哪里检查？\n\n先检查图鉴标注的牌组版本，再对照教材说的是哪张牌、哪个位置。若教材标了画师，优先按画师和牌名找到对应插图。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n### 我只想学习牌面，需要翻一张随机牌吗？\n\n直接在图鉴按牌名打开魔术师即可。查到指定的图像以后，可以把页上的简短牌义提示放在观察记录下一行。\n\n[Cardloom · official readings and local journal](https://cardloom.site/) · [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## Glossary\n\n- **韦特–史密斯牌面**: 此处指 Cardloom 的魔术师牌义页标注为 1909 年原画的那幅图。 [Cardloom · official readings and local journal](https://cardloom.site/)\n\n- **画面观察**: 可以指给另一位读者看的位置、形状或物件。写下你看到的内容后，再记录自己想到的含义。 [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) · [Wenbu · calculation conventions](https://wenbu.app/methodology/)\n\n## Evidence notes\n\n- Cardloom 将首页展示的牌组介绍为 1909 年经典版。 — “the classic 1909 deck” (fact); [Cardloom · official readings and local journal](https://cardloom.site/)\n\n- 问卜使用自己的 AI 插画，并为牌配短提示。 — “Wenbu uses the full deck with original AI illustrations and short reading prompts.” (fact); [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md)\n\n- 问卜日签的练习建议先观察画面，再读关键词。 — “先看看牌上的细节，再读关键词。” (editorial); [Wenbu · daily card](https://wenbu.app/daily/)\n\n## Sources\n\n- [Current complete zh canonical article](https://wenbu.app/knowledge/zh/compare-cardloom.md) — Current public original and earlier additions; add substantial coverage without repeating or replacing them.; fetched 2026-11-13T13:03:53.907Z; complete response\n\n- [Current complete en canonical article](https://wenbu.app/knowledge/en/compare-cardloom.md) — Current public original and earlier additions; add substantial coverage without repeating or replacing them.; fetched 2026-11-13T13:03:53.925Z; complete response\n\n- [Cardloom · official readings and local journal](https://cardloom.site/) — Vendor statements about browser draws, physical-deck logging, local journal export and optional AI; no account, storage or security audit; fetched 2026-11-13T13:03:53.972Z; complete response\n\n- [Wenbu · calculation conventions](https://wenbu.app/methodology/) — First-party implementation; not evidence of predictive accuracy; fetched 2026-11-13T13:03:53.966Z; complete response\n\n- [Wenbu · tarot beginner guide](https://wenbu.app/knowledge/en/tarot-beginner.md) — Existing editorial and worked reading; fetched 2026-11-13T13:03:53.971Z; excerpt\n\n- [Wenbu · versioned public capabilities](https://wenbu.app/capabilities.json) — First-party current tool, convention and privacy contract; not external endorsement or predictive validation; fetched 2026-11-13T13:03:53.966Z; complete response\n\n- [Wenbu · daily card](https://wenbu.app/daily/) — Current first-party product UI; not a personal forecast; fetched 2026-11-13T13:03:53.964Z; complete response\n\n[从问卜塔罗页打开牌图鉴](https://wenbu.app/tarot/)","edition":{"title":"看魔术师的牌面时，选 Cardloom 还是问卜？","description":"用两份公开图鉴对照同一张魔术师。查经典韦特–史密斯画面时找 Cardloom，想练习对照不同画法时再翻问卜图鉴。","answer":"教材要你找魔术师头顶的无限符号时，先看 Cardloom 的牌义页。它把这幅图标为 1909 年韦特–史密斯原画，人物头顶可见黑色横置八字。问卜图鉴的同一位置画了带放射线的金色圆盘。把两张图并排看，还能核对共有的举手姿势和桌面道具。","answerSourceIds":["cardloom","tarot","methods"],"evidence":[{"claim":"Cardloom 将首页展示的牌组介绍为 1909 年经典版。","sourceId":"cardloom","quote":"the classic 1909 deck","kind":"fact"},{"claim":"问卜使用自己的 AI 插画，并为牌配短提示。","sourceId":"tarot","quote":"Wenbu uses the full deck with original AI illustrations and short reading prompts.","kind":"fact"},{"claim":"问卜日签的练习建议先观察画面，再读关键词。","sourceId":"daily","quote":"先看看牌上的细节，再读关键词。","kind":"editorial"}],"takeaways":["先确认教材引用的是哪套牌，再查它提到的细节。","先看人物头顶，再看举起的手和桌面。抄下一个保留的细节和一个变化。","记录图鉴名称、牌名和核对日期，方便日后找回同一幅画。"],"sections":[{"heading":"从教材提到的物件出发","paragraphs":["如果教材在讲帕梅拉·科尔曼·史密斯画的魔术师，从 Cardloom 首页的 Card meanings 进入，打开 The Magician。该页把图标为 1909 年原画。黄底上能看到人物头顶的黑色无限符号和手里举起的白色杖。","在问卜塔罗工具页点「翻阅 78 张牌图鉴」，找到魔术师并打开图面。问卜把这套画标为以传统意象重新绘制的原创 AI 插画。这一版人物头顶是放射光芒的金色圆盘，抬起的手里握着带叶子的枝条。"],"sourceIds":["cardloom","tarot","methods"]},{"heading":"给两张图各记一条可以核对的描述","paragraphs":["从人物头顶移到桌面，两幅画上都能找到杯、剑和带五角星的圆盘。如果教程把某件道具叫作「星币」，可以先记下图上的形状。下一位读者凭形状和位置就能找到同一件东西。","两幅图和图鉴入口均于 2026 年 11 月 13 日核对。读特定教材时，选教材所指的版本。练习比较画法时，打开两页，在笔记里写明图鉴名称。牌义提示可以另写一行。"],"sourceIds":["cardloom","tarot","daily"]}],"figure":{"title":"给一张牌做两栏观察","caption":"用牌名找到同一张牌，再按固定顺序看头顶、手势和桌面。","sourceIds":["cardloom","tarot","daily"],"steps":[{"label":"查经典牌面","detail":"在 Cardloom 的 Card meanings 打开 The Magician，先看人物头顶。"},{"label":"打开重绘版","detail":"在问卜图鉴打开魔术师，看同一块位置和举起的手。"},{"label":"留两条记录","detail":"记一个共同细节和一个不同细节，注明来源图鉴和日期。"}]},"table":{"title":"两张魔术师图的观察位置","columns":["观察位置","Cardloom","问卜"],"rows":[["图鉴的版本标识","牌义页标为 1909 年韦特–史密斯原画","图鉴标为根据传统意象重绘的原创 AI 插画"],["人物头顶","黑色横置八字","有光芒的金色圆盘"],["举起的手","白色杖","带叶子的枝条"],["桌面上都能找到的物件","杯、剑、带五角星的圆盘","杯、剑、带五角星的圆盘"]],"sourceIds":["cardloom","tarot","methods"]},"example":{"title":"练习查教材里提到的无限符号","intro":"假设一段入门教材请你在魔术师头顶找无限符号。这里用两张已核对的公开插图演示如何定位，不需要抽牌。","steps":["在 Cardloom 打开 Card meanings，选 The Magician。把位置记为人物头顶，形状记为黑色横置八字。","在问卜塔罗页打开牌图鉴，选魔术师。查看同一位置，把形状记为金色圆盘与放射线。","在两张图上各找一次杯或剑，给这件共同道具单独留一行。","在笔记里把无限符号归到 Cardloom 展示的版本，给问卜的金色圆盘单留一行。回看教材时，你可以直接找到它描述的那幅图。"],"conclusion":"核对答案是 Cardloom 图有教材描述的符号，问卜图的同一位置用了金色圆盘。举手动作和若干桌面道具可以作为跨版本的比对线索。","sourceIds":["cardloom","tarot","methods"]},"faq":[{"question":"图上找不到教材说的符号，要回到哪里检查？","answer":"先检查图鉴标注的牌组版本，再对照教材说的是哪张牌、哪个位置。若教材标了画师，优先按画师和牌名找到对应插图。","sourceIds":["cardloom","tarot","methods"]},{"question":"我只想学习牌面，需要翻一张随机牌吗？","answer":"直接在图鉴按牌名打开魔术师即可。查到指定的图像以后，可以把页上的简短牌义提示放在观察记录下一行。","sourceIds":["cardloom","tarot","methods"]}],"glossary":[{"term":"韦特–史密斯牌面","definition":"此处指 Cardloom 的魔术师牌义页标注为 1909 年原画的那幅图。","sourceIds":["cardloom"]},{"term":"画面观察","definition":"可以指给另一位读者看的位置、形状或物件。写下你看到的内容后，再记录自己想到的含义。","sourceIds":["tarot","methods"]}],"cta":{"label":"从问卜塔罗页打开牌图鉴","reason":"点击「翻阅 78 张牌图鉴」，选魔术师，核对头顶和桌面的细节。"}},"editionScope":"addition","sources":[{"id":"current-zh","title":"Current complete zh canonical article","url":"https://wenbu.app/knowledge/zh/compare-cardloom.md","role":"Current public original and earlier additions; add substantial coverage without repeating or replacing them.","fetchedAt":"2026-11-13T13:03:53.907Z","hash":"e1f1ebc5f501fb2a28e5fdf48fb799162fbb3d72108de96e794b0aa0f66bbfbe","truncated":false},{"id":"current-en","title":"Current complete en canonical article","url":"https://wenbu.app/knowledge/en/compare-cardloom.md","role":"Current public original and earlier additions; add substantial coverage without repeating or replacing them.","fetchedAt":"2026-11-13T13:03:53.925Z","hash":"cd9349ead6c6e25f76e18feee44848b03bbb47173e83cfb16b7cf28fca0f6423","truncated":false},{"id":"cardloom","title":"Cardloom · official readings and local journal","url":"https://cardloom.site/","role":"Vendor statements about browser draws, physical-deck logging, local journal export and optional AI; no account, storage or security audit","fetchedAt":"2026-11-13T13:03:53.972Z","hash":"686e21405a77d65bcff6804f3b4ee7a799c91106ddbd1468b3fadb033bada7f2","truncated":false},{"id":"methods","title":"Wenbu · calculation conventions","url":"https://wenbu.app/methodology/","role":"First-party implementation; not evidence of predictive accuracy","fetchedAt":"2026-11-13T13:03:53.966Z","hash":"21a7f433eb1571ce23e4c4e96f09d0da54c2f9030469f4b8ecfc294a13344de5","truncated":false},{"id":"tarot","title":"Wenbu · tarot beginner guide","url":"https://wenbu.app/knowledge/en/tarot-beginner.md","role":"Existing editorial and worked reading","fetchedAt":"2026-11-13T13:03:53.971Z","hash":"b4354be906ffdc106924853aeafb7243c1cf5665765f1f2ebbb99e28486f2527","truncated":true},{"id":"capabilities","title":"Wenbu · versioned public capabilities","url":"https://wenbu.app/capabilities.json","role":"First-party current tool, convention and privacy contract; not external endorsement or predictive validation","fetchedAt":"2026-11-13T13:03:53.966Z","hash":"557485b2f5513f237e8258ecf9d0a1fbbf5aa19a30c726f9199bf3817e021546","truncated":false},{"id":"daily","title":"Wenbu · daily card","url":"https://wenbu.app/daily/","role":"Current first-party product UI; not a personal forecast","fetchedAt":"2026-11-13T13:03:53.964Z","hash":"d0aa0ed4d2a4b181cb0f77100aa04017e4d946adc62304495a3ca39a674020cb","truncated":false}],"previousAdditions":[{"zh":{"title":"问卜与 Cardloom：网页抽牌、本地手记与可选账号保存怎么选？","description":"按“抽牌—保留原始结果—导出或保存”的实际任务，比较问卜与 Cardloom 的公开说明：网页抽牌、本地手记、导出与账号选项。含一个假设的三张牌记录案例，并说明设备更换后的恢复未经验证。","answer":"先看你的任务终点。若你只想在浏览器里抽一次牌、写几句自己的话、把记录留在本机并随时导出，问卜与 Cardloom 的公开页面都覆盖了这条路径：Cardloom 写明免费、无需账号、手记留在本浏览器，并提示换设备或清除浏览器数据前先导出；问卜的免费页列出 78 张塔罗抽牌、本地手记与 JSON 导出，且当前无需付款或注册。若你希望抽牌之外还能把同一套计算交给自己的 Agent，问卜公开了 MCP、CLI 与 REST 接口，Cardloom 的页面则描述可选的 AI 解读，每天最多三次。两者都没有在公开摘录中给出设备更换后的恢复保证，因此不要把“有导出”理解成“换机后一定找得回”。选择依据应是：你更看重可导出的本地记录，还是更看重可编程的接口与多工具计算。","answerSourceIds":["cardloom","wenbu","agents","methods"],"evidence":[{"claim":"Cardloom 的公开页面写明阅读与本地手记免费、无需账号，并提示换设备前先导出。","sourceId":"cardloom","quote":"Free readings · No account","kind":"fact"},{"claim":"问卜免费页列出 78 张塔罗抽牌、本地手记与 JSON 导出，当前无需付款或注册。","sourceId":"wenbu","quote":"78 张塔罗抽牌、本地手记、JSON 导出","kind":"fact"},{"claim":"问卜的塔罗抽牌由程序随机抽取，页面保留原始结果，计算可复现不代表解释已被科学验证。","sourceId":"methods","quote":"塔罗和在线起卦由程序随机抽取。页面会保留原始结果。","kind":"editorial"}],"takeaways":["先确定终点：只要本地记录与导出，两者都覆盖；需要可编程接口时，问卜的公开文档更完整。","Cardloom 明确提示换设备或清除浏览器数据前先导出；问卜也提供 JSON 导出，但两者都未公开设备更换后的恢复保证。","抽牌是随机过程，重复提问不会按需复现同一组牌；记录的价值在于保留当时的结果与你的笔记。"],"sections":[{"heading":"先定义任务：抽牌、留底、再决定去向","paragraphs":["把选择拆成三步会更清楚：先抽一个牌阵，再把原始结果连同问题与笔记保存下来，最后决定是导出成本地副本，还是交给账号或外部工具。Cardloom 的公开页面把这条路径写得很直白：选择牌阵、翻牌、写可选笔记，然后保存到我的手记，并说明手记留在本浏览器、换设备或清除浏览器数据前应先导出。问卜的免费页同样列出 78 张塔罗抽牌、本地手记与 JSON 导出，且当前无需付款或注册。","差别在于这条路径之外的延伸。问卜的公开文档还描述了 MCP 的 draw_tarot 工具，输入为 1 或 3 张、是否逆位，从完整牌组不放回抽取；CLI 与 REST 也以 JSON 返回结果。Cardloom 的页面则描述可选的 AI 解读，写明每天最多三次，并说明只有你选择提交的问题、牌与笔记才会送给模型。两者都适合抽完就记，但如果你想把结果交给自己的程序或 Agent，问卜公开的接口说明更具体。"],"sourceIds":["cardloom","wenbu","agents","methods"]},{"heading":"本地手记与导出：两者都强调先留副本","paragraphs":["Cardloom 对手记位置的表述很明确：手记留在本浏览器，导出副本是为了留个安全备份或带到另一台设备。这句话同时说明了两件事：默认存储是本地的，以及跨设备需要你自己搬运文件。问卜的免费页把本地手记与 JSON 导出并列为免费功能，并说明 AI 额度用完后仍可抽牌、保存手记和导出结果。就公开文字而言，两者都把导出当作读者自己的动作，而不是自动同步。","需要保留的不确定性是：两份公开摘录都没有描述导出文件的字段结构、导入后的校验方式，也没有给出设备更换后恢复成功的保证。因此能导出只证明存在一个导出入口，不证明换机后一定能完整还原。若记录对你重要，稳妥做法是导出后自己打开文件确认内容，并保留一份与浏览器无关的副本；这是操作建议，不是任何一方公开承诺的存储保证。"],"sourceIds":["cardloom","wenbu"]},{"heading":"账号、AI 与接口：按需选择，不比较谁更强","paragraphs":["Cardloom 的页面写明阅读、牌义、课程与本地手记免费，没有结账或订阅；AI 模型解读限制为每浏览器每天三次。问卜的免费页则说明浏览器访客与登录账号每天最多 5 次工具页 AI 解读、12 回合 Agent 对话，按上海时间零点重置，登录会归并当天试用用量而不会重新赠送。这些是各自公开的额度说明，不能据此推断对方的定价或未公开的限制。","在接口方面，问卜公开了 MCP 的七种工具、CLI 与 REST 的 JSON 返回，并说明计算请求不需要问卜账户，只有选择内置 AI 时才把所选内容进一步交给模型。Cardloom 的公开摘录没有描述 API 或导出格式；但这只说明该页面没有覆盖这些内容，不能据此断定 Cardloom 不具备相关能力。比较时应把页面没写与产品没有分开。"],"sourceIds":["cardloom","wenbu","agents"]},{"heading":"随机性与记录：为什么重复提问不等于复现","paragraphs":["问卜的方法页说明，塔罗从 78 张牌中等概率抽取 1 张或 3 张，同一次抽取不会重复；开启逆位时每张牌独立有 50% 概率呈逆位，三张牌的位置是当下、牵引、下一步，用于组织思考而非必然顺序。这意味着抽牌结果由随机过程产生，你重复同一个问题，并不会按需得到同一组牌；偶尔重复只是巧合。","因此记录的重点不是验证牌准不准，而是保留当时抽到了什么、你写了什么、后来发生了什么。Cardloom 的日签说明建议保留一句笔记，到晚上再看看自己注意到了什么；它没有给出“把提示当作可选小实验”或“区分牌面联想与实际发生”的规则。问卜的日签页才明确建议把提示当成可选择的小实验，并分清牌面让我想到的和实际发生的。问卜的方法页要求把传统含义、AI 推断与现实情况分开看待；Cardloom 的页面把牌义说明称为现代反思提示，但没有陈述同样的三层规则。"],"sourceIds":["methods","cardloom","daily"]}],"figure":{"title":"从抽牌到换设备的决策流程","caption":"该流程把抽牌、留底、导出、换设备拆成可检查的步骤，并标出公开说明未覆盖的环节。它描述的是操作顺序，不是任何一方的存储保证。","sourceIds":["cardloom","wenbu","methods"],"steps":[{"label":"1. 抽牌并保留原始结果","detail":"在网页上选择一个牌阵并翻牌；问卜的方法页说明抽牌为随机过程，页面保留原始结果，不要为了更好看而重抽。"},{"label":"2. 写下问题与笔记","detail":"Cardloom 把笔记列为可选，问卜也提供本地手记；记录问题、牌位与当时的想法，便于日后回看。"},{"label":"3. 导出本地副本","detail":"Cardloom 提示换设备或清除浏览器数据前先导出；问卜免费页列出 JSON 导出。导出后应自己打开文件确认内容。"},{"label":"4. 换设备时自行搬运","detail":"两份公开摘录都未说明设备更换后的恢复流程或成功保证，因此把导出文件当作需要自己保管的副本，而不是自动同步。"}]},"table":{"title":"按任务对照两份公开说明","columns":["任务环节","Cardloom 公开说明","问卜公开说明","未验证或未覆盖"],"rows":[["网页抽牌","选择牌阵、翻牌，含每日一张、三张牌与自定义牌阵","78 张塔罗抽牌，1 或 3 张，完整牌组不放回","两者的抽牌界面细节未逐一测试"],["本地手记","手记留在本浏览器，笔记可选","本地手记，免费页列为免费功能","导出文件的字段结构未在摘录中说明"],["导出","可导出与导入手记，提示换设备前先导出","JSON 导出","导入后的校验与设备更换恢复未验证"],["账号与 AI","免费、无需账号；可选 AI 每天最多三次","免费无需注册；AI 额度按访客与账号分别说明","账号保存与同步状态未做实测"],["可编程接口","公开摘录未描述","MCP、CLI、REST 返回 JSON","Cardloom 是否有接口未由该页面证明"]],"sourceIds":["cardloom","wenbu","agents","methods"]},"example":{"title":"假设案例：一次三张牌记录如何走完导出与换设备","intro":"以下为虚构示例，用于演示记录流程，不代表任何真实抽牌结果，也不是计算出的命盘。假设读者小林在浏览器里就是否接受一个新项目抽三张牌，位置为当下、牵引、下一步，并写下笔记。","steps":["第一步：抽牌。小林在网页上选择三张牌阵，翻牌后看到三张牌与正逆位状态。按问卜方法页的说明，这是一次随机抽取，同一次抽取不重复；她不为更顺而重抽。","第二步：留底。她把问题、三张牌的名称与正逆位、以及一句自己的观察写进手记。Cardloom 的页面把笔记列为可选，并说明手记留在本浏览器；问卜也提供本地手记。","第三步：导出。她使用导出功能生成一份本地副本，并立刻打开文件，确认三张牌、位置与笔记都在。Cardloom 提示换设备或清除浏览器数据前先导出；问卜免费页列出 JSON 导出。","第四步：换设备。她换了一台电脑，尝试把副本带过去。两份公开摘录都没有描述导入后的校验或恢复保证，因此这一步的结果属于未测试范围；她只能确认自己手里有一份可读的副本。","第五步：回看。几周后她对照笔记与实际进展，区分牌面让我想到的和实际发生的，不把任何一方的解释当作预测结论。"],"conclusion":"这个案例能教的具体一点是：记录的价值来自原始牌面、位置、自己的笔记和一份自己确认过的副本，而不是来自重复抽牌或某个准确率说法。设备更换后能否完整恢复，公开说明没有给出保证，应如实标为未验证。","sourceIds":["cardloom","wenbu","methods"]},"faq":[{"question":"两者都免费、都无需账号，那还比什么？","answer":"比的是任务终点。若你只要网页抽牌、本地手记与导出，两者公开说明都覆盖；若你还想把抽牌结果交给自己的程序或 Agent，问卜公开了 MCP、CLI 与 REST 的 JSON 返回，Cardloom 的公开摘录没有描述接口。反过来，Cardloom 页面明确写了可选 AI 解读每天最多三次，这也是它公开说明的一部分。","sourceIds":["cardloom","wenbu","agents"]},{"question":"导出之后，换设备一定能恢复吗？","answer":"不能这样承诺。Cardloom 提示换设备或清除浏览器数据前先导出，问卜列出 JSON 导出，但两份公开摘录都没有描述导入校验或设备更换后的恢复保证。稳妥做法是导出后自己打开文件确认内容，并保留一份与浏览器无关的副本；设备更换后的恢复属于未测试范围。","sourceIds":["cardloom","wenbu"]},{"question":"重复问同一个问题，会抽到同一组牌吗？","answer":"不会按需复现。问卜方法页说明塔罗由程序随机抽取，同一次抽取不重复；重复提问是新的随机过程，偶尔重复只是巧合。记录应保留当时抽到的牌与笔记，而不是靠重抽去凑一个想要的结果。","sourceIds":["methods"]},{"question":"Cardloom 页面没写 API，是不是就没有？","answer":"不能这样推断。公开摘录只覆盖该页面写到的内容，没有描述 API 或导出格式，只说明该页面未涉及这些主题，不等于产品不具备相关能力。比较时应把页面没写和产品没有分开，并以各自公开说明为准。","sourceIds":["cardloom","agents"]}],"glossary":[{"term":"本地手记","definition":"保存在当前浏览器中的阅读记录，通常需要读者自己导出副本才能在换设备或清除数据后保留。","sourceIds":["cardloom","wenbu"]},{"term":"不放回抽取","definition":"从完整牌组中抽牌，同一次抽取中每张牌最多出现一次；问卜的 draw_tarot 工具按此规则抽取 1 或 3 张。","sourceIds":["agents","methods"]},{"term":"逆位","definition":"牌面呈倒置状态的一种读法选项；问卜说明开启逆位时每张牌独立有 50% 概率呈逆位。","sourceIds":["methods"]},{"term":"导出副本","definition":"由读者主动生成、可保存在浏览器之外的文件；存在导出入口不等于承诺换设备后自动恢复。","sourceIds":["cardloom","wenbu"]}],"cta":{"label":"先抽一次三张牌，写下笔记并导出一份副本","reason":"这能让你在真实操作中确认记录是否完整、导出文件是否可读，再决定是否需要账号或接口；设备更换后的恢复仍需自行验证。"}},"en":{"title":"Wenbu vs Cardloom: browser draws, local journal and optional account saving","description":"Compare Wenbu and Cardloom on the concrete task of drawing a spread, keeping the raw result, then exporting or saving. Includes a hypothetical three-card record and states plainly that recovery after a device change was not tested.","answer":"Start with where your task ends. If you only want to draw in a browser, write a few notes and keep the record locally with an export option, both public pages cover that path: Cardloom says readings and the local journal are free with no account, that the journal stays in this browser, and that you should export before changing devices or clearing browser data. Wenbu's free page lists 78-card tarot draws, a local journal and JSON export, currently without payment or registration. If you also want to hand the same calculation to your own agent, Wenbu publishes MCP, CLI and REST interfaces, while Cardloom's page describes optional AI interpretation limited to three per day. Neither public excerpt promises recovery after a device change, so do not read \"export exists\" as \"you will always get it back.\" Choose by whether you value a portable local record or programmable interfaces and multi-tool calculation.","answerSourceIds":["cardloom","wenbu","agents","methods"],"evidence":[{"claim":"Cardloom's public page says readings and the local journal are free with no account, and advises exporting before changing devices.","sourceId":"cardloom","quote":"Free readings · No account","kind":"fact"},{"claim":"Wenbu's free page lists 78-card tarot draws, a local journal and JSON export, currently without payment or registration.","sourceId":"wenbu","quote":"78 张塔罗抽牌、本地手记、JSON 导出","kind":"fact"},{"claim":"Wenbu's tarot draws are random, the page keeps the raw result, and reproducibility of a calculation does not validate an interpretation.","sourceId":"methods","quote":"塔罗和在线起卦由程序随机抽取。页面会保留原始结果。","kind":"editorial"}],"takeaways":["Decide the endpoint first: both cover local records and export; Wenbu's public documentation goes further on programmable interfaces.","Cardloom explicitly advises exporting before changing devices or clearing browser data; Wenbu offers JSON export, but neither excerpt guarantees recovery after a device change.","Draws are random, so repeating a question does not reproduce the same cards on demand; the record's value is the original result plus your notes."],"sections":[{"heading":"Define the task: draw, keep the raw result, then decide where it goes","paragraphs":["Splitting the choice into three steps helps: draw a spread, save the raw result with your question and notes, then decide whether to export a local copy or hand it to an account or external tool. Cardloom's public page states this path plainly: choose a spread, turn the cards, write optional notes, then save to the journal, while noting that the journal stays in this browser and should be exported before changing devices or clearing browser data. Wenbu's free page likewise lists 78-card tarot draws, a local journal and JSON export, currently without payment or registration.","The difference lies beyond that path. Wenbu's public documentation also describes an MCP draw_tarot tool taking one or three cards and an upright/reversed option, drawing without replacement from the full deck; its CLI and REST also return JSON. Cardloom's page describes optional AI interpretation, limited to three per day, and says only the question, cards and notes you choose to submit are sent to the model. Both suit drawing and noting it down, but if you want to pass results to your own program or agent, Wenbu's interface documentation is more specific."],"sourceIds":["cardloom","wenbu","agents","methods"]},{"heading":"Local journal and export: both say keep a copy","paragraphs":["Cardloom is explicit about where the journal lives: in this browser, with export described as a way to keep a safe copy or take it to another device. That sentence implies two things at once: storage is local by default, and moving across devices is your job. Wenbu's free page lists the local journal and JSON export as free features and says that after AI quota runs out you can still draw, save notes and export results. On the public text, both treat export as a reader action rather than automatic sync.","The uncertainty to preserve is this: neither public excerpt describes the export file's fields, the validation after import, or any guarantee that recovery succeeds after a device change. So export exists proves an export entry point, not that a new device will restore everything. If the record matters, open the exported file yourself to confirm its contents and keep a copy independent of the browser; that is operational advice, not a storage promise from either vendor."],"sourceIds":["cardloom","wenbu"]},{"heading":"Accounts, AI and interfaces: choose by need, not by a winner","paragraphs":["Cardloom's page says readings, card meanings, lessons and the local journal are free, with no checkout or subscription, and limits AI model interpretations to three per day on this browser. Wenbu's free page says browser visitors and signed-in accounts get up to five tool-page AI interpretations and twelve agent turns per day, resetting at midnight Shanghai time, and that signing in merges the day's trial usage rather than granting a fresh allowance. These are each vendor's own quota statements; they do not establish the other's pricing or undisclosed limits.","On interfaces, Wenbu publishes seven MCP tools, CLI and REST JSON returns, and says calculation requests need no Wenbu account, with only the built-in AI sending selected content onward. Cardloom's public excerpt does not describe an API or export format; that only means the page does not cover those topics, not that Cardloom lacks such features. Keep not on the page separate from not in the product."],"sourceIds":["cardloom","wenbu","agents"]},{"heading":"Randomness and records: why repeating a question is not reproduction","paragraphs":["Wenbu's methodology page says tarot draws one or three cards with equal probability from 78, with no repeats within a single draw; when reversals are on, each card independently has a 50% chance of appearing reversed, and the three positions are present, pull and next step, used to organize reflection rather than as a necessary sequence. The result therefore comes from a random process: repeating the same question will not give you the same cards on demand, and an occasional repeat is coincidence.","So the point of a record is not to test whether the cards are accurate, but to keep what was drawn, what you wrote and what later happened. Cardloom's daily-card text advises keeping a note and seeing what you notice by evening; it does not state a rule about treating the prompt as an optional small experiment or separating card associations from what actually happened. Wenbu's daily-card page is the one that explicitly suggests treating the prompt as a small experiment you can choose and separating what the card made you think of from what actually happened. Wenbu's methodology page asks readers to keep traditional meanings, AI inference and real circumstances apart; Cardloom's page calls its card notes modern prompts for reflection but does not state the same three-layer rule."],"sourceIds":["methods","cardloom","daily"]}],"figure":{"title":"Decision flow from draw to device change","caption":"This flow splits draw, keep a copy, export and change device into checkable steps and marks where the public statements stop. It describes an operating order, not a storage guarantee from either vendor.","sourceIds":["cardloom","wenbu","methods"],"steps":[{"label":"1. Draw and keep the raw result","detail":"Choose a spread and turn the cards; Wenbu's methodology page says draws are random and the page keeps the raw result, so do not redraw just to get a nicer-looking spread."},{"label":"2. Write the question and notes","detail":"Cardloom lists notes as optional and Wenbu offers a local journal; record the question, positions and your thoughts at the time for later review."},{"label":"3. Export a local copy","detail":"Cardloom advises exporting before changing devices or clearing browser data; Wenbu's free page lists JSON export. Open the file yourself to confirm its contents."},{"label":"4. Move it yourself on a new device","detail":"Neither public excerpt describes a recovery process or success guarantee after a device change, so treat the export as a copy you must keep, not automatic sync."}]},"table":{"title":"Task-by-task comparison of the two public statements","columns":["Task step","Cardloom public statement","Wenbu public statement","Not verified or not covered"],"rows":[["Browser draw","Choose a spread and turn cards; daily card, three-card and custom spreads","78-card tarot draws, one or three cards, without replacement","Detailed draw interfaces were not individually tested"],["Local journal","Journal stays in this browser; notes optional","Local journal listed as a free feature","Export file fields are not described in the excerpts"],["Export","Export and import journal; export before changing devices","JSON export","Import validation and device-change recovery were not tested"],["Account and AI","Free, no account; optional AI up to three per day","Free, no registration; AI quota described for visitors and accounts","Account saving and sync status were not tested"],["Programmable interface","Not described in the public excerpt","MCP, CLI and REST returning JSON","Whether Cardloom has an API is not proven by this page"]],"sourceIds":["cardloom","wenbu","agents","methods"]},"example":{"title":"Hypothetical case: a three-card record through export and a device change","intro":"This is a fictional example for illustrating the record-keeping flow. It is not a real draw result and not a computed birth chart. Suppose a reader, Lin, draws three cards in a browser about whether to accept a new project, using the positions present, pull and next step, and writes a note.","steps":["Step 1: draw. Lin chooses a three-card spread and turns the cards, seeing three cards and their upright or reversed states. Per Wenbu's methodology page this is a random draw with no repeats within it; she does not redraw to get a smoother result.","Step 2: keep a record. She writes the question, the three card names and orientations, and one observation into the journal. Cardloom's page lists notes as optional and says the journal stays in this browser; Wenbu also offers a local journal.","Step 3: export. She uses the export function to create a local copy and immediately opens the file to confirm the three cards, positions and note are present. Cardloom advises exporting before changing devices or clearing browser data; Wenbu's free page lists JSON export.","Step 4: change device. She moves to another computer and tries to bring the copy along. Neither public excerpt describes validation after import or a recovery guarantee, so this step falls outside what was tested; she can only confirm she holds a readable copy.","Step 5: review. Weeks later she compares the note with what actually happened, separating what the cards made her think of from what happened, and does not treat either vendor's interpretation as a prediction."],"conclusion":"The specific lesson is that a record's value comes from the raw cards, positions, your own notes and a copy you have checked, not from redrawing or an accuracy claim. Whether a device change restores everything is not guaranteed by the public statements and should be labeled untested.","sourceIds":["cardloom","wenbu","methods"]},"faq":[{"question":"Both are free and need no account, so what is there to compare?","answer":"The endpoint of your task. If you only need browser draws, a local journal and export, both public statements cover it; if you also want to pass draws to your own program or agent, Wenbu publishes MCP, CLI and REST JSON returns, while Cardloom's public excerpt does not describe an interface. Cardloom's page does explicitly describe optional AI interpretation limited to three per day, which is part of its public statement.","sourceIds":["cardloom","wenbu","agents"]},{"question":"After exporting, is recovery on a new device guaranteed?","answer":"No such promise can be made. Cardloom advises exporting before changing devices or clearing browser data, and Wenbu lists JSON export, but neither public excerpt describes import validation or a recovery guarantee after a device change. Open the exported file to confirm its contents and keep a copy independent of the browser; device-change recovery remains untested.","sourceIds":["cardloom","wenbu"]},{"question":"Will asking the same question again draw the same cards?","answer":"Not on demand. Wenbu's methodology page says tarot is drawn randomly and a single draw has no repeats; repeating a question starts a new random process, and an occasional repeat is coincidence. Keep the cards and notes from the original draw rather than redrawing to reach a preferred result.","sourceIds":["methods"]},{"question":"If Cardloom's page does not mention an API, does that mean there is none?","answer":"That cannot be inferred. The public excerpt covers only what the page states; it does not describe an API or export format, which means the page does not address those topics, not that the product lacks them. Keep not on the page separate from not in the product and rely on each vendor's own statements.","sourceIds":["cardloom","agents"]}],"glossary":[{"term":"Local journal","definition":"A reading record stored in the current browser, which usually requires the reader to export a copy to keep it after changing devices or clearing data.","sourceIds":["cardloom","wenbu"]},{"term":"Draw without replacement","definition":"Drawing from the full deck so each card appears at most once in a single draw; Wenbu's draw_tarot tool draws one or three cards this way.","sourceIds":["agents","methods"]},{"term":"Reversal","definition":"An option to read a card upside down; Wenbu says each card independently has a 50% chance of appearing reversed when reversals are on.","sourceIds":["methods"]},{"term":"Exported copy","definition":"A file the reader creates and can keep outside the browser; an export entry point is not a promise of automatic recovery on a new device.","sourceIds":["cardloom","wenbu"]}],"cta":{"label":"Draw one three-card spread, write a note and export a copy","reason":"This lets you confirm in practice whether the record is complete and the exported file is readable before deciding whether you need an account or an interface; recovery after a device change still needs your own verification."}},"topic":{"id":"compare-cardloom","slug":"cardloom","category":"compare","mode":"new","tool":"tarot","zh":"问卜与 Cardloom：网页抽牌、本地手记与可选账号保存怎么选？","en":"Wenbu vs Cardloom: browser draws, local journal and optional account saving","task":"Help a reader choose between Wenbu and Cardloom for a concrete tarot drawing or record-keeping task, using only each vendor's public statements.","unique":"Compare two browser-based tarot workspaces on the exact reader task: draw a spread, keep the raw result, then decide whether to export or save to an account. Cardloom's public page describes browser draws, physical-deck logging, local journal export and optional AI; Wenbu's free page lists 78-card draws, local notes and JSON export. Include one hypothetical three-card record followed through export and a device change, stating plainly that recovery after a device change was not tested. Do not invent pricing, account tests, storage guarantees or accuracy rankings.","sources":["cardloom","wenbu","agents","methods"],"priority":82,"search":{"pillar":"agent-choice","intent":"compare","zh":["Cardloom 对比","网页塔罗抽牌记录","塔罗本地手记导出","塔罗工具怎么选"],"en":["Cardloom vs Wenbu","browser tarot journal export","tarot app comparison","local tarot journal"],"basis":"research_hypothesis"}},"revision":"cbda229f48e6c1c9e61089fdc2c3c09043913dc170e82ee88d61d724ee2d3b43","updatedAt":"2026-10-30T07:03:56.905Z","sources":[{"id":"cardloom","title":"Cardloom · official readings and local journal","url":"https://cardloom.site/","role":"Vendor statements about browser draws, physical-deck logging, local journal export and optional AI; no account, storage or security audit","fetchedAt":"2026-10-30T07:00:36.246Z","hash":"686e21405a77d65bcff6804f3b4ee7a799c91106ddbd1468b3fadb033bada7f2","truncated":false},{"id":"wenbu","title":"Wenbu · current free access","url":"https://wenbu.app/free/","role":"First-party access and quota documentation","fetchedAt":"2026-10-30T07:00:36.222Z","hash":"db9ca0345476ac248c364369edcc1736928f02903c6de6c3a9653fa610d6d2f7","truncated":false},{"id":"agents","title":"Wenbu · agent integrations","url":"https://wenbu.app/agents/","role":"Current first-party product documentation","fetchedAt":"2026-10-30T07:00:36.235Z","hash":"93a965358202f2256f2d430a517a7cc192c950b3e6f6157a242a234d3c24a7d8","truncated":false},{"id":"methods","title":"Wenbu · calculation conventions","url":"https://wenbu.app/methodology/","role":"First-party implementation; not evidence of predictive accuracy","fetchedAt":"2026-10-30T07:00:36.212Z","hash":"5452dbc076e1c31aa334fa49949d682ad7851e75a5cf9396b6682530b30f0f0c","truncated":false},{"id":"daily","title":"Wenbu · daily card","url":"https://wenbu.app/daily/","role":"Current first-party product UI; not a personal forecast","fetchedAt":"2026-10-30T07:00:36.220Z","hash":"b2bab9f05c80e8d1d3298bad705319173d94b421ad87546cfe94f8eb0ecc9999","truncated":false},{"id":"capabilities","title":"Wenbu · versioned public capabilities","url":"https://wenbu.app/capabilities.json","role":"First-party current tool, convention and privacy contract; not external endorsement or predictive validation","fetchedAt":"2026-10-30T07:00:36.222Z","hash":"557485b2f5513f237e8258ecf9d0a1fbbf5aa19a30c726f9199bf3817e021546","truncated":false}]}]}