读咚咚 (Read DongDong) - 个人知识数据层的命令行接口
Project description
读咚咚 (Read) - 个人知识数据层
读咚咚是个人知识数据层的 Python 库,提供 CLI、SDK 和 MCP Server 等多种访问方式。
本地、私有、可编程的个人知识基础设施。
简介
读咚咚 是一个个人知识数据层,以 Core Library 为核心资产,支持多种客户端访问。
当你看到一句有启发的话、一篇好文章,快速存下来。CLI、浏览器插件、Agent 都可以访问这些数据。
核心特点
- 数据层优先 - Core Library 是核心,CLI/插件/SDK 都是客户端
- 本地私有 - 数据存放在
~/.read/read.db,不上云、不同步、不追踪 - Agent 友好 - JSON 输出 + Python SDK + MCP Server(v0.2)
- 极简核心 - 只做收集,不做整理
安装
方式一:从 PyPI 安装(推荐)
pip install read-cli
方式二:从源码安装
git clone https://github.com/gudong/read.git
cd read
pip install -e .
初始化
read init
安装 Agent Workspace
如果你使用 OpenClaw,可以把 agent 目录复制到工作区:
# 复制 agent workspace
mkdir -p ~/.openclaw/agents/read
cp -r agent/* ~/.openclaw/agents/read/
# 从模板创建 MEMORY.md
cp agent/MEMORY.md.template ~/.openclaw/agents/read/MEMORY.md
快速开始
# 添加摘录
read add "开始,就是最好的时机"
# 收藏文章
read add --url "https://mp.weixin.qq.com/s/xxx"
# 列出所有
read ls
# 搜索
read search "AI"
# 删除
read delete 123 --force
项目结构
read/
├── src/read/ # CLI 源码
├── agent/ # Agent workspace(OpenClaw 使用)
│ ├── IDENTITY.md # Agent 身份
│ ├── SOUL.md # Agent 性格
│ ├── TOOLS.md # CLI 工具定义
│ └── MEMORY.md.template # 记忆模板
├── docs/ # 文档
├── tests/ # 测试
├── pyproject.toml # Python 包配置
└── README.md # 本文件
Python SDK
from read import Client
client = Client()
# 添加
item = client.add("开始,就是最好的时机")
# 列出
items = client.list(limit=10)
# 搜索
results = client.search("AI")
命令参考
| 命令 | 说明 |
|---|---|
read init |
初始化数据库 |
read add "内容" |
添加摘录 |
read add --url "..." |
收藏链接 |
read ls |
列出所有 |
read search "关键词" |
搜索 |
read get 123 |
获取单条 |
read delete 123 |
删除 |
架构设计
┌─────────────────────────────────────────────────────────┐
│ 客户端层 │
├──────────────┬──────────────┬──────────────┬────────────┤
│ CLI │ Browser │ Python SDK │ MCP Server │
│ (read add) │ Extension │ (import) │ (Agent) │
└──────────────┴──────────────┴──────────────┴────────────┘
│
┌────────▼────────┐
│ Core Library │
│ (read.core.Client)│
└────────┬────────┘
│
┌────────▼────────┐
│ SQLite DB │
│ ~/.read/read.db │
└─────────────────┘
路线图
| 版本 | 核心资产 | 客户端 | 状态 |
|---|---|---|---|
| v0.1 | Core Library v0.1 | CLI | ✅ 完成 |
| v0.2 | Core Library v0.1 | MCP Server | 🚧 开发中 |
| v0.3 | Core Library v0.1 | Python SDK 增强 | 📋 计划中 |
| v0.4 | Core Library v0.1 | Browser Extension | 📋 计划中 |
文档
License
作者
让 AI 看见你的知识。
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
dong_read-0.3.2.tar.gz
(36.3 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
dong_read-0.3.2-py3-none-any.whl
(18.1 kB
view details)
File details
Details for the file dong_read-0.3.2.tar.gz.
File metadata
- Download URL: dong_read-0.3.2.tar.gz
- Upload date:
- Size: 36.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b62ae31b86b39b434012a53aa98a034e4c8fb10de92a4d9a2f4d100caf5badc1
|
|
| MD5 |
166563659ee833fbf2c9ba6c60eee211
|
|
| BLAKE2b-256 |
e2853e363ada755571e08bc5538bc1ee5a7986abfcec84dd17bb88fc16a0f902
|
File details
Details for the file dong_read-0.3.2-py3-none-any.whl.
File metadata
- Download URL: dong_read-0.3.2-py3-none-any.whl
- Upload date:
- Size: 18.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7337029191511ab4dc86cdeac2d109b703dcccf8e63c09be51ccdf4ccb645b68
|
|
| MD5 |
a488f1a1c4eace9df867b014072cb6c8
|
|
| BLAKE2b-256 |
5b5c31132eecf13b663c8f87c9bd8a97aaf88c87706eb364e59fc86c42a3ce8c
|