Mailuo (脉络 mai) — 支持多用户注册隔离、跨机器同步与多 Agent (pi.dev / Google agy) 的脉络管理系统
解决跟多个 Agent 对话时“单窗口穿插杂事导致上下文混乱”、“多窗口/跨机器碎片化找不到历史讨论”的核心痛点。
1. 任意机器一键安装 (pip install)
在其他任何机器的 Python 环境中,直接通过 GitHub 仓库一键安装:
pip install git+https://github.com/EeroEternal/mailuo.git
# 或者克隆仓库后本地安装:
# pip install .
(无需在其他机器上安装 Node.js / Wrangler 或配置 Cloudflare 密钥,客户端会自动连接已部署的 Cloudflare Worker 多租户网关 https://mailuo-api.lipeng-sh.workers.dev 并将数据加密隔离保存在 Cloudflare D1 mailuo-db 中。)
2. 账号注册与多机器登录(每个人的数据严格隔离、绝不串号)
第一次在某台机器上使用 mai 时,会自动引导你注册或登录(也可以显式执行命令):
# 1) 注册属于你自己的账号(自动登录并生成本地凭证 ~/.mailuo/auth.json)
mai register <用户名> <密码>
# 或者交互式输入密码(不回显):
mai register
# 2) 在另一台电脑上登录同一个账号,立即无缝接续所有历史脉络
mai login <用户名> <密码>
# 3) 查看当前登录的是谁
mai whoami
# 4) 退出当前机器的账号
mai logout
3. 极简日常用法 (mai)
# 1) 直接对话(自动路由:延续话题 / 穿插提问隔离 / 调出旧话题 / 整理核心主题)
mai "我想讨论一下在 Cloudflare D1 上存储多 Agent 脉络的架构方案"
# 2) 临时穿插无关问题(自动进入隔离沙箱,绝不污染当前话题摘要)
mai "顺便问一下,帮我写个匹配邮箱的正则"
# 3) 自然语言调出历史话题 Session
mai "上次我们讨论的那个 Cloudflare D1 架构的话题调出来"
# 4) 在当前话题脉络下直接拉起 pi.dev 或 Google agy
mai pi # 直接进入 pi.dev 交互式 TUI(自动绑定当前话题的 --session-id,退出后自动同步记录到你的云端账号)
mai pi "帮我分析一下这段代码" # 用 pi.dev 单次回答并记录到当前话题
mai agy # 直接进入 Google Antigravity (agy) 交互式界面
# 5) 查看你账号下的所有具体话题与整理核心主题
mai ls # 查看当前账号下的所有 Topic Sessions
mai themes # 把当前账号下的零散 Session 自动整理成『最核心主题』
mai sync # 将当前机器上的 ~/.pi/agent/sessions 和 ~/.gemini/antigravity-cli/brain 同步至你的云端账号
# 6) 进入交互式控制台
mai
Metadata
Release files for mailuo 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| mailuo-0.2.0.tar.gz | 38.8 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mailuo-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 77.0 kB
Release files / mailuo-0.2.0.tar.gz
| Download URL | mailuo-0.2.0.tar.gz |
|---|---|
| Size | 38.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1b9f3575818672f83c492fca951aeec5e215ce9117e16bf420ede832dcc7ca95
|
|
BLAKE2b-256 checksum How to use checksums |
ed08f7707c0d2dee3aee6e0a9ed9bf9f7a3281bccc0c78056ebd07960258b82b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.8
|
Release files / mailuo-0.2.0-py3-none-any.whl
| Download URL | mailuo-0.2.0-py3-none-any.whl |
|---|---|
| Size | 38.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
677498fb6222d90cf5e42871453ff42330e7dd2604e0d4d277c13074b91d49e7
|
|
BLAKE2b-256 checksum How to use checksums |
46a12bbbb5e3634471b6cb8287ae6e86c004ec10f6c812e33b89a495cc6c9dfa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.8
|
Security for mailuo 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.