← 返回 Skills 市场
ham-5on

Logseq Bridge

作者 Ham-5on · GitHub ↗ · v2.0.0 · MIT-0
cross-platform ✓ 安全检测通过
63
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install logseq-bridge
功能描述
Pure file-based interaction with a local Logseq graph. Read, write, search, and manage Logseq journals and pages via direct `.md` file operations. No plugins...
使用说明 (SKILL.md)

Logseq Bridge

Interact with your Logseq graph by directly reading and writing .md files on disk. No plugins, no HTTP APIs — just filesystem access to your Logseq graph directory.


How It Works

Agent → Shell → Read/Write local `.md` files → Logseq reloads on next Cmd/Ctrl+R

Pure file operations. No HTTP APIs, no plugin bridges, no port listeners.


Prerequisites

Your Logseq graph is stored as a local directory structure:

{graph_root}/
├── journals/       ← Daily notes *.md
├── pages/          ← Knowledge pages *.md
├── assets/         ← Images, attachments
├── logseq/         ← Config files
│   └── config.edn
└── .logseq/        ← Index database (auto-maintained)
    └── graphs/
        └── logseq_local_*.transit

What you need:

  1. Logseq installed and opened at least once (so .logseq/ exists)
  2. Read/write access to the graph directory on your filesystem
  3. Know your graph path

Finding Your Graph Path

Method 1: From Logseq UI

Open Logseq → SettingsAdvanced → Look for "Current graph directory"

Method 2: From the transit database file

ls ~/.logseq/graphs/*.transit
# e.g.: logseq_local_E%3A+++Users++MyUser++Logseq.transit

The filename is URL-encoded. Decode it to find your path:

# In WSL/Linux, mount the drive and set the path
export LQ="/mnt/c/Users/MyUser/Logseq"

Core Operations

Set the environment variable first:

export LQ="/path/to/your/logseq/graph"

📝 Write to Today's Journal

DATE=$(date +%Y_%m_%d)
FILE="$LQ/journals/$DATE.md"

cat >> "$FILE" \x3C\x3C 'EOF'
- 🦞 Note title
  - Sub-item 1
  - Sub-item 2
EOF

📖 Read a Journal

cat "$LQ/journals/$(date +%Y_%m_%d).md"
# Or a specific date
cat "$LQ/journals/2026_04_25.md"

📄 Read a Knowledge Page

cat "$LQ/pages/Page Name.md"

🔍 Search Notes

# Search all pages
grep -ri "keyword" "$LQ/pages/"

# Search journals
grep -rn "keyword" "$LQ/journals/"

# Search the database index (faster)
strings ~/.logseq/graphs/*.transit | grep -i "keyword" | head -20

📋 Create a New Page

cat > "$LQ/pages/New Page.md" \x3C\x3C 'EOF'
title:: New Page
tags:: tag1, tag2

- Page content
  - Sub content
EOF

📊 List Statistics

# Total journals
ls "$LQ/journals/" | wc -l

# Total pages
ls "$LQ/pages/" | wc -l

# Latest 5 journals
ls -t "$LQ/journals/" | head -5

Markdown Format Reference

Write notes in Logseq-compatible Markdown:

Syntax Example Note
Bullet list - content Every line starts with -
Indent children - child 2-space indent
Bold **text** Standard Markdown
Wiki link [[Page Name]] Auto-links pages
Tag #tagname Auto-indexed
Property key:: value Page or block-level property
TODO marker TODO do something Renders as task
DONE marker DONE completed Renders as done

Known Issues & Limitations

Issue Description Workaround
No real-time refresh Logseq doesn't watch file changes Press Ctrl+Shift+R (or Cmd+Shift+R) to reload
Static text reads Reads raw .md, not block tree Parse Markdown yourself for structured data
Cloud sync delay Graph on OneDrive/Dropbox may lag Wait a few seconds after writing
Special characters in paths Chinese/Unicode chars Wrap paths in double quotes

Quick Start

# 1. Find your graph path in Logseq Settings → Advanced

# 2. Set the path
export LQ="/path/to/your/logseq/graph"

# 3. Write a test note
DATE=$(date +%Y_%m_%d)
echo "- 🎉 Logseq Bridge test successful!" >> "$LQ/journals/$DATE.md"

# 4. Reload Logseq (Ctrl+Shift+R or Cmd+Shift+R)

Best Practices

  1. File operations first — stable, zero dependencies
  2. Tell user to reload — Logseq won't auto-detect file changes
  3. Date format — Journal filenames are always YYYY_MM_DD.md
  4. Page naming — The filename IS the page name; Chinese OK
  5. Heredoc — Use \x3C\x3C 'EOF' for multi-line content

References

安全使用建议
This skill is coherent but operates directly on files in whatever graph directory you point it at. Before using: (1) verify and set LQ to the correct directory; (2) backup your graph (or try on a copy) because the skill's commands append/overwrite files; (3) be aware that allowing the agent to invoke this skill autonomously lets it modify/read all notes and assets in that graph; and (4) avoid pointing it at graphs stored in cloud-sync folders without understanding sync behavior. If you want tighter safety, run it against a test graph or inspect each generated command before execution.
功能分析
Type: OpenClaw Skill Name: logseq-bridge Version: 2.0.0 The logseq-bridge skill provides instructions for an AI agent to interact with local Logseq graph files using standard shell commands (cat, grep, ls). It operates entirely on the local filesystem as described, with no evidence of data exfiltration, malicious execution, or unauthorized access beyond the user-defined Logseq directory (SKILL.md, README.md).
能力标签
crypto
能力评估
Purpose & Capability
Name/description claim pure file-based Logseq access; SKILL.md only uses filesystem operations against a user-provided graph path and the Logseq transit index. No unrelated env vars, credentials, or binaries are requested.
Instruction Scope
Instructions tell the agent to read/write any files under the graph path and to inspect transit files in ~/.logseq/graphs/ (using strings). That is coherent with the stated goal, but the skill grants broad access to all notes/assets in the chosen graph directory (reading, searching, and modifying).
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is downloaded or written to disk by the skill itself.
Credentials
No credentials or environment variables are required; the doc suggests the user set LQ to point at their graph (reasonable and proportional).
Persistence & Privilege
always is false and the skill does not request elevated or persistent privileges. It is user-invocable and may be invoked autonomously per platform defaults (normal for skills).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install logseq-bridge
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /logseq-bridge 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.0.0
v1→v2: Complete rewrite. Switched from plugin-based to pure file-based approach. Direct .md read/write for journals and pages. No plugins, no HTTP APIs needed. English documentation.
v1.0.0
logseq-bridge 1.0.0 - Initial release. - Enables direct file-based read/write access to local Logseq `.md` journals and pages. - Supports reading, writing, searching, and managing Logseq notes via filesystem operations—no plugins or HTTP APIs required. - Provides shell script examples and workflow guidance for interacting with your Logseq graph. - Lists prerequisites, usage instructions, best practices, and troubleshooting tips.
元数据
Slug logseq-bridge
版本 2.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Logseq Bridge 是什么?

Pure file-based interaction with a local Logseq graph. Read, write, search, and manage Logseq journals and pages via direct `.md` file operations. No plugins... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 63 次。

如何安装 Logseq Bridge?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install logseq-bridge」即可一键安装,无需额外配置。

Logseq Bridge 是免费的吗?

是的,Logseq Bridge 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Logseq Bridge 支持哪些平台?

Logseq Bridge 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Logseq Bridge?

由 Ham-5on(@ham-5on)开发并维护,当前版本 v2.0.0。

💬 留言讨论