Oraclebone

io.github.sapuyou45-bit由 GitHub 账号 sapuyou45-bit 发布v8.2.0更新于 Oct 24, 2026

Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results.

已验证STDIO仅桌面

概览

AI 生成的概览

本地 MCP 服务器,用可审计的脚本抽取塔罗牌、起易经卦、小六壬与八字盘,交由助手解读。

可以做什么
  • 按牌组、牌阵与逆位选项抽取塔罗牌
  • 以铜钱或蓍草起易经卦,给出本卦与变卦
  • 按数字或公历时间回退方式起小六壬
  • 按公历出生时间排出八字(四柱)盘
  • 获取指定方法的解读模板
  • 结果均以 JSON 返回并附带方法元数据,模型只解读而不自行编造结果
适用场景
适合希望助手给出可复现、可审计的占卜式解读,用于反思、决策梳理或创意破局,并在既定安全边界内解读而非凭空生成结果时使用。
运行要求
以本地 stdio 进程运行;需安装 oraclebone Python 包(Python 3,无其他运行时依赖),并在宿主中配置 ai-divination-mcp 命令。八字功能需要可选的 lunar-python 附加包。未声明需要账号、密钥或网络访问。
安装前请注意
项目声明不适用于医疗、法律、财务或危机指导,也不是占卜有效性的科学证明,解读仅为象征性反思。README 另提供 shell 安装脚本,会把技能目录复制到代理技能目录,从而在你的机器上写入文件;若不希望如此,请改用包安装。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Oraclebone,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Oraclebone

Three thousand years ago, Shang kings carved their divinations into bone — the first auditable record of an oracle at work. Oraclebone brings the same discipline to AI agents: audited scripts produce the draw, the hexagram, the pillars; the model only interprets what it is given. It never invents the result.

English | 简体中文 | 日本語

Demo

[oraclebone demo: pip install, tarot draw, I Ching cast, MCP server stdio]

[tests] [release] [PyPI] [PyPI Downloads] [Latest release] [License: MIT] [Python] [GitHub Discussions]

🔮 Open-source divination toolkit for AI agents, formerly known as ai-divination-skills (renamed in v8.0.0 — the old PyPI package is frozen; install oraclebone instead).

oraclebone is a practical skill collection for tarot, I Ching, Xiao Liu Ren, and future symbolic systems. It is built for agent workflows that need auditable randomness, clear method boundaries, and reusable interpretation templates.

This project treats divination as symbolic reasoning and reflection, not deterministic prediction.

⚡ One-line Install for AI Agents

Paste this into your AI agent:

text
Install Oraclebone for this agent: https://raw.githubusercontent.com/sapuyou45-bit/oraclebone/main/docs/install.md

Or install directly for Claude-style local skills:

bash
curl -fsSL https://raw.githubusercontent.com/sapuyou45-bit/oraclebone/main/install.sh | bash

The default target is ~/.claude/skills. Set AI_SKILLS_DIR for another agent skill directory.

✨ Overview

Most AI divination prompts let the model invent the result. This repo separates the two jobs:

  1. A local script produces the card draw, hexagram, or Xiao Liu Ren position.
  2. The AI agent interprets that generated result with clear safety boundaries.

That makes readings easier to test, reproduce, audit, and reuse across agents.

🧭 Methodological Rigor

The core rule is simple: scripts or user-provided physical casts generate the divination result; AI interprets that result and does not generate the divination result.

This is not scientific proof of divination efficacy. It is a stricter workflow for symbolic reasoning:

  • real readings use system randomness by default
  • seeded mode is only for tests and reproducible demos
  • traditional methods and limitations are documented per skill
  • JSON outputs include enough metadata to audit the method
  • approximate modes emit warnings instead of pretending to be traditional

🌐 Multilingual Docs

The GitHub Pages site ships a six-language switcher — 简体中文, English, 日本語, Português, 한국어, Español. It follows your browser language by default and remembers your manual choice.

Open the published site

Local preview:

bash
python3 -m http.server 8000 -d docs

Published site:

text
https://sapuyou45-bit.github.io/oraclebone/

🧩 Included Skills

SkillWhat it doesScript
tarotDraws tarot cards for reflection, decisions, creative blocks, and project reframing.skills/tarot/scripts/draw.py
ichingCasts six-line I Ching hexagrams with primary and resulting hexagrams.skills/iching/scripts/cast.py
xiaoliurenCasts Xiao Liu Ren from lunar-style numbers or a Gregorian time fallback.skills/xiaoliuren/scripts/cast.py
baziCasts a Bazi (Four Pillars / 八字) chart from a Gregorian birth datetime. Requires the optional lunar-python extra.skills/bazi/scripts/cast.py

🚀 Quick Start

Install from PyPI:

bash
pip install oraclebone

Or from a checkout:

bash
pip install .

Use editable mode while developing:

bash
pip install -e .

Use one command for every system:

bash
ai-divination tarot --deck major --spread three-card --reversalsai-divination iching --method yarrowai-divination xiaoliuren --method numbers --month 3 --day 12 --hour 7

Ask for an agent interpretation template:

bash
ai-divination template tarot

Use the Python API directly:

python
from oraclebone.tarot import drawfrom oraclebone.iching import castfrom oraclebone.xiaoliuren import cast_numbers

You can still run the underlying scripts directly:

bash
python3 skills/tarot/scripts/draw.py --deck major --spread three-card --reversalspython3 skills/iching/scripts/cast.py --method coinspython3 skills/iching/scripts/cast.py --method yarrowpython3 skills/xiaoliuren/scripts/cast.py --method numbers --month 3 --day 12 --hour 7

Use a seed for reproducible demos:

bash
python3 skills/tarot/scripts/draw.py --spread decision --seed demopython3 skills/iching/scripts/cast.py --method yarrow --seed demo

All scripts output JSON.

📦 Install as Agent Skills

For AI-agent-guided setup, use the remote install runbook:

text
Install Oraclebone for this agent: https://raw.githubusercontent.com/sapuyou45-bit/oraclebone/main/docs/install.md

For direct shell install:

bash
curl -fsSL https://raw.githubusercontent.com/sapuyou45-bit/oraclebone/main/install.sh | bash

The installer copies tarot, iching, and xiaoliuren into ~/.claude/skills by default. To target another agent, set AI_SKILLS_DIR before running it.

Manual install is just copying the folders you want into your agent's skill directory:

bash
mkdir -p ~/.claude/skillscp -R skills/tarot ~/.claude/skills/tarotcp -R skills/iching ~/.claude/skills/ichingcp -R skills/xiaoliuren ~/.claude/skills/xiaoliuren

Each skill is self-contained:

text
skills/name/  SKILL.md  agents/openai.yaml  scripts/  references/

Install individual folders, not the entire repository, when you only want one skill.

Each skill script also works in single-folder mode. If the Python package is installed, the script delegates to the package runtime. If only the skill folder is copied, it falls back to the bundled standalone script in that skill.

Per-host adapters

Every skill ships four adapter files in skills/<skill>/agents/:

HostFileHow it is invoked
OpenAI / Codex skillsopenai.yamlSkill metadata + brand icons.
Claude Desktop / claude.ai project skillsclaude.yamlTool spec that runs ai-divination <skill>.
Gemini CLI / Gemini Extensionsgemini.yamlExtension manifest that runs the same CLI.
Cursorcursor.mdcRule file with hard "never invent the draw" guard.

All four adapters route through the same audited ai-divination <skill> CLI, so the agent host never invents the result.

🧠 Use it from Claude Desktop / Codex / any MCP host

oraclebone ships a built-in MCP server (ai-divination-mcp). Any Model Context Protocol host — Claude Desktop, Codex, Continue, Cursor — can mount it with a single config line, and the model gets five tools: tarot_draw, iching_cast, xiaoliuren_cast, bazi_cast, and interpretation_template.

The model never invents the draw; the server runs the audited scripts locally.

Claude Desktop

Install the package once:

bash
pip install oraclebone

Then edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "divination": {      "command": "ai-divination-mcp"    }  }}

Restart Claude Desktop. Ask "draw three tarot cards for my decision" — Claude will call tarot_draw and interpret the JSON output.

Codex / Continue / Cursor

Any MCP-aware host follows the same pattern. The server speaks JSON-RPC 2.0 over stdio with no third-party dependencies.

Per-client setup guides

Copy-paste JSON configs and example prompts for each host:

🤖 Agent Behavior

Each skill instructs the agent to:

  • generate or accept a concrete draw/cast result
  • read concise reference material only when needed
  • interpret with the shared response contract
  • avoid certainty, fatalism, and professional advice

Shared guidance lives in:

  • shared/methodology.md
  • shared/interpretation-protocol.md
  • shared/response-contract.md
  • shared/randomness-protocol.md
  • shared/safety-policy.md
  • shared/interpretation-style.md

🧪 Examples

  • examples/tarot-decision.md
  • examples/iching-strategy.md
  • examples/xiaoliuren-daily.md

🛡️ Safety Boundaries

These skills are not for medical, legal, financial, or crisis guidance.

Good readings should:

  • frame the result as symbolic reflection
  • connect claims to the generated result
  • preserve user agency
  • offer small, reversible next steps
  • state uncertainty clearly

See ETHICS.md for the full project stance.

🛠️ Development

No runtime dependencies are required beyond Python 3.

Run tests:

bash
python3 -m unittest discover -s tests

Current coverage checks:

  • unified CLI routing
  • package-only CLI execution
  • importable Python APIs
  • single-folder skill execution
  • skill metadata and asset contracts
  • interpretation protocol templates
  • tarot spread output
  • I Ching cast structure and manual lines
  • Xiao Liu Ren number and time fallback behavior

💬 Community

🗺️ Roadmap

Near-term:

  • Add a published package workflow.
  • Expand automated skill validation in CI.
  • Add richer reference material for each MVP skill.
  • Add more example readings.
  • Add more agent integration examples.

Later:

  • meihua
  • liuyao
  • runes
  • numerology
  • astrology

📄 License

MIT

来源:README.md,提交 a9a8ab7

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v8.2.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分