AgriciDaniel / claude-obsidian

查看原文 / View Original 编辑 / Edit

AgriciDaniel / claude-obsidian

claude-obsidian Build an Obsidian knowledge base that becomes more useful every time you use it. Capture sources, create connected notes, retrieve grounded answers, and keep the vault healthy—without giving up ownership of your files. See the workflow · Quick start · Explore the skills · Installation guide · Windows & WSL

claude-obsidian 构建一个随着使用频率增加而愈发有用的 Obsidian 知识库。你可以捕获来源、创建关联笔记、检索有据可查的答案，并保持知识库的健康状态——且无需放弃对文件的所有权。查看工作流 · 快速入门 · 探索技能 · 安装指南 · Windows & WSL

claude-obsidian is a local-first knowledge system for Claude Code and compatible Agent Skills hosts. It turns source material into linked, source-cited Obsidian pages; answers from the evidence already in the vault; and provides explicit workflows for research, retrieval, maintenance, and visual mapping. Your vault remains a normal directory of Markdown, JSON, and source files. It is not hidden in a plugin cache, locked in a cloud database, or silently uploaded to a model.

claude-obsidian 是一个为 Claude Code 和兼容的 Agent Skills 主机设计的“本地优先”知识系统。它能将原始素材转化为带有引用链接的 Obsidian 页面；基于知识库中已有的证据回答问题；并为研究、检索、维护和可视化映射提供明确的工作流。你的知识库始终是一个包含 Markdown、JSON 和源文件的普通目录。它不会被隐藏在插件缓存中，不会被锁定在云端数据库中，也不会被静默上传到模型中。

From source to living knowledge

Most AI note workflows stop after saving text. claude-obsidian is organized around a repeatable loop: retain the source, ground the claims, connect the knowledge, then put it back to work.

从来源到鲜活的知识

大多数 AI 笔记工作流在保存文本后就停止了。claude-obsidian 围绕一个可重复的循环进行组织：保留来源、夯实论点、连接知识，然后将其重新投入使用。

  • Capture with context. Bring local sources through a visible inbox and preserve immutable, content-addressed copies before synthesis.

  • Ground every important claim. Source and claim ledgers retain authority, freshness, support, contradiction, confidence, and review state.

  • Connect what you learn. Build linked pages, indexes, Maps of Content, methodology-aware structures, and Obsidian Canvas views.

  • Use the vault again. Query, research, retrieve, lint, and fold what is already known instead of starting every conversation from zero.

  • 带上下文捕获。 通过可见的收件箱引入本地来源，并在综合处理前保留不可变的、基于内容寻址的副本。

  • 夯实每一个重要论点。 来源和论点分类账保留了权威性、时效性、支持性、矛盾性、置信度和审查状态。

  • 连接所学知识。 构建链接页面、索引、内容地图 (MOC)、方法论感知结构以及 Obsidian Canvas 视图。

  • 再次利用知识库。 查询、研究、检索、检查（lint）并整理已知内容，而不是每次对话都从零开始。

See the vault

The output is meant to remain useful with or without an agent: plain Markdown for portability, Obsidian for navigation and visual exploration. Linked knowledge in Graph view · A visual knowledge map in Obsidian Canvas

查看知识库

其输出旨在无论是否有 AI 代理参与都能保持有用：纯 Markdown 格式确保了可移植性，Obsidian 确保了导航和视觉探索的便利性。图谱视图中的关联知识 · Obsidian Canvas 中的可视化知识地图

Why it feels different

  • Local by default. The vault is user-owned and works as ordinary files. Network egress is a separate, explicit decision.
  • Sources survive the summary. Notes point back to durable source evidence; unsupported and contradictory claims remain visible.
  • Knowledge compounds deliberately. Ingestion, querying, linting, retrieval, research, and rollups share one provenance-aware model.
  • Parallel agents cannot race the vault. Workers return drafts. One orchestrator inspects and applies one recoverable transaction.
  • Capabilities are stated honestly. Optional tools are detected, maturity is declared, and missing adapters degrade clearly instead of being simulated. This is not an automatic transcript recorder, a cloud sync service, a factual oracle, or a substitute for backups and source control.

为什么它与众不同

  • 默认本地化。 知识库由用户所有，并以普通文件形式存在。网络出口是独立且明确的决策。
  • 来源优于摘要。 笔记指向持久的原始证据；不支持的或矛盾的论点依然可见。
  • 知识刻意积累。 摄入、查询、检查、检索、研究和汇总共享同一个具备溯源能力的模型。
  • 并行代理不会造成知识库冲突。 工作者返回草稿。由一个协调器检查并应用一个可恢复的事务。
  • 能力诚实声明。 可选工具会被检测，成熟度会被声明，缺失的适配器会清晰地降级，而不是进行模拟。这不是自动转录记录器、云同步服务、事实预言机，也不是备份和版本控制的替代品。

Quick start

The safest first run uses a source checkout and a separate user vault. Every mutating setup command previews its exact operation before it can apply.

快速入门

最安全的首次运行方式是使用源码检出和一个独立的个人知识库。每一个会产生变动的设置命令在应用前都会预览其确切操作。

1. Get the product

git clone https://github.com/AgriciDaniel/claude-obsidian.git
cd claude-obsidian

The checkout contains the product. It is not your knowledge vault.

1. 获取产品

git clone https://github.com/AgriciDaniel/claude-obsidian.git
cd claude-obsidian

检出的内容包含产品本身，它不是你的知识库。

2. Initialize a separate vault

export GENERATED_AT="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
export OPERATION_ID="init-reviewed"
python3 scripts/claude-obsidian.py init "$HOME/Documents/MyKnowledgeVault" \
  --generated-at "$GENERATED_AT" --operation-id "$OPERATION_ID"

Review the JSON plan and copy its approved_plan_sha256, then apply that exact operation:

python3 scripts/claude-obsidian.py init "$HOME/Documents/MyKnowledgeVault" \
  --generated-at "$GENERATED_AT" --operation-id "$OPERATION_ID" \
  --approved-plan-sha256 "<sha256-from-the-plan>" --apply

For an existing Obsidian vault, use the non-destructive adopt workflow described in the installation guide.

2. 初始化独立知识库

export GENERATED_AT="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
export OPERATION_ID="init-reviewed"
python3 scripts/claude-obsidian.py init "$HOME/Documents/MyKnowledgeVault" \
  --generated-at "$GENERATED_AT" --operation-id "$OPERATION_ID"

审查 JSON 计划并复制其 approved_plan_sha256，然后应用该确切操作：

python3 scripts/claude-obsidian.py init "$HOME/Documents/MyKnowledgeVault" \
  --generated-at "$GENERATED_AT" --operation-id "$OPERATION_ID" \
  --approved-plan-sha256 "<sha256-from-the-plan>" --apply

对于现有的 Obsidian 知识库，请使用安装指南中描述的非破坏性“采用（adopt）”工作流。

3. Start from the vault Open the new directory in Obsidian, then run Claude Code from that directory with the local plugin:

cd "$HOME/Documents/MyKnowledgeVault"
claude --plugin-dir /absolute/path/to/claude-obsidian

Start with: /claude-obsidian:wiki Then place a source in inbox/ and invoke /claude-obsidian:wiki-ingest. Save an answer explicitly with /claude-obsidian:save; ask the vault with /claude-obsidian:wiki-query.

3. 从知识库开始 在 Obsidian 中打开新目录，然后从该目录运行带有本地插件的 Claude Code：

cd "$HOME/Documents/MyKnowledgeVault"
claude --plugin-dir /absolute/path/to/claude-obsidian

从以下命令开始：/claude-obsidian:wiki 然后将来源放入 inbox/ 并调用 /claude-obsidian:wiki-ingest。使用 /claude-obsidian:save 显式保存答案；使用 /claude-obsidian:wiki-query 向知识库提问。

For Codex, OpenCode, or Gemini, preview and then apply the portable skill links from the product checkout:

bash bin/setup-multi-agent.sh --host codex
bash bin/setup-multi-agent.sh --host codex --apply

Cursor and Windsurf use workspace-local skill discovery. Marketplace setup, every supported host, vault adoption, upgrades, and uninstall steps are covered in the full installation guide.

对于 Codex、OpenCode 或 Gemini，请预览并应用来自产品检出目录的可移植技能链接：

bash bin/setup-multi-agent.sh --host codex
bash bin/setup-multi-agent.sh --host codex --apply

Cursor 和 Windsurf 使用工作区本地的技能发现功能。市场设置、所有支持的主机、知识库采用、升级和卸载步骤均包含在完整安装指南中。

15 skills, one system

The skills are small enough to invoke directly and coordinated enough to share the same evidence, vault-selection, and mutation rules.

15 种技能，一个系统

这些技能足够小，可以直接调用，且协调性良好，能够共享相同的证据、知识库选择和变动规则。

(Table omitted for brevity, but the structure remains consistent)

Claude Code exposes namespaced invocations such as /claude-obsidian:wiki-lint; other hosts use their native Agent Skills invocation. Trigger phrases and exact contracts live in each skills/<name>/SKILL.md. Trust is part of the architecture. The product never treats…

Claude Code 暴露了命名空间调用，例如 /claude-obsidian:wiki-lint；其他主机使用其原生的 Agent Skills 调用方式。触发短语和确切契约位于每个 skills/<name>/SKILL.md 中。信任是架构的一部分。该产品从不将……

← 返回新闻列表 / Back to news list