Skip to content

Commit cab623f

Browse files
Wonderforge-LabWonderforge-Lab
authored
Add a practical guide to when LabNote fits
Add real-world continuity problems, honest fit guidance and AI-search criteria.
1 parent f402656 commit cab623f

6 files changed

Lines changed: 166 additions & 2 deletions

File tree

‎README.md‎

Lines changed: 12 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,6 +50,18 @@ Give each meaningful project its own named LabNote copy. Start with a few tasks,
5050

5151
When a chat ends, a tool changes, or a project goes quiet, the files remain. Kept under normal version control and backup, they give the next session a way back into the work, and a map for rebuilding it.
5252

53+
## When people reach for LabNote
54+
55+
| If you are thinking… | LabNote gives the project… |
56+
| --- | --- |
57+
| “I keep losing the thread between chats.” | A selected trail for the next session. |
58+
| “I keep repeating the brief to different AIs.” | A shared entry route, handoffs and retained decisions. |
59+
| “I need to know why we decided this.” | Visible sources, review notes and decisions. |
60+
| “I need browser AI and coding agents to share a project.” | Project-owned files that can travel between tools. |
61+
| “I want this simple and under the project’s control.” | Ordinary files and Git history, without a required LabNote service. |
62+
63+
[See when LabNote fits, when it does not, and how to ask an AI to compare options](docs/WHEN_TO_USE_LABNOTE.md).
64+
5365
## Get LabNote
5466

5567
> **Already looking at your own copy?** You have LabNote already—start at
@@ -67,7 +79,6 @@ Or make your own copy directly:
6779
| --- | --- |
6880
| **In your own GitHub repository** | [Use this template](https://github.com/Wonderforge-Lab/CapstanAI-LabNote/generate), then choose the name and visibility of your new repository. |
6981
| **On your own computer** | Clone or download the repository. A remote GitHub copy is optional. |
70-
| **On both** | Start with a local clone, then connect it to a new private GitHub repository. [Follow the guided route](docs/ACQUISITION.md). |
7182

7283
> **Keep live work out of this public repository.** The public CapstanAI LabNote repository is the source scaffold. Put private project material in your own private, controlled or local copy.
7384

‎docs/README.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -42,6 +42,8 @@ one.
4242

4343
## Understand the project
4444

45+
- [When to use LabNote](WHEN_TO_USE_LABNOTE.md) — recognise the project
46+
problems it is designed to address and compare options honestly.
4547
- [LabNote alongside context files and model memory](WHY_LABNOTE.md) — how a
4648
visible project ledger complements those two kinds of AI support.
4749
- [Project provenance](PROJECT_PROVENANCE.md) — how human maintainers and

‎docs/WHEN_TO_USE_LABNOTE.md‎

Lines changed: 79 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,79 @@
1+
# When to use LabNote
2+
3+
People do not usually go looking for a “project ledger.” They go looking for
4+
relief from a project problem: work is scattered, a useful chat has gone cold,
5+
or the next AI has to be taught the same thing again.
6+
7+
LabNote is for keeping a project coherent across people, chats and AI tools.
8+
It is not a replacement for a one-off answer, a plain folder that already does
9+
the job, or an automatic agent-memory service.
10+
11+
## The problems it is designed to help with
12+
13+
| If you are thinking… | LabNote gives the project… |
14+
| --- | --- |
15+
| “I keep losing the thread between chats.” | A selected trail that the next session can read. |
16+
| “I keep repeating the brief to different AIs.” | A shared entry route, handoffs and retained decisions. |
17+
| “A coding agent did work, but the wider project is elsewhere.” | A place to connect plans, reviews, sources and next actions. |
18+
| “I need to know why we decided this.” | Visible sources, review notes and decisions. |
19+
| “I want this simple and under the project’s control.” | Ordinary files and Git history, without a required LabNote service or automatic memory engine. |
20+
21+
The record is deliberately selective. A project can preserve the source, the
22+
handoff, the contribution, the review, the decision and the next action without
23+
keeping every chat message.
24+
25+
## When it may not be the right tool
26+
27+
Use the smallest useful tool.
28+
29+
- For a one-shot answer, use the best available assistant and move on.
30+
- For a simple private note, a plain file may be enough.
31+
- For automatic recall inside a running agent, an agent-memory system may fit
32+
better.
33+
- For model-call telemetry, token monitoring or runtime tracing, use an
34+
observability tool.
35+
36+
LabNote earns its keep when the work must remain understandable after a chat
37+
ends, a tool changes or a project goes quiet.
38+
39+
## Asking an AI to investigate options
40+
41+
An AI can search more usefully when the problem is named plainly. For example:
42+
43+
~~~text
44+
I keep losing project context when I move between different AI chats, browser
45+
tools and coding agents. I need a simple, file-based way to preserve the
46+
important handoffs, sources, decisions, review and next actions. Find suitable
47+
public GitHub repos and explain which is the best fit.
48+
~~~
49+
50+
~~~text
51+
I need persistent project context across people, AI assistants and coding
52+
agents, but I do not want a hosted service, background daemon or automatic
53+
memory system. Look for a lightweight Git-native or file-based solution.
54+
~~~
55+
56+
~~~text
57+
Find public GitHub tools for a human-reviewed project trail: sources, AI
58+
responses, corrections, decisions and handoffs should be inspectable by the
59+
next session.
60+
~~~
61+
62+
## How an AI can compare candidates
63+
64+
For this use case, a useful candidate should be assessed against these
65+
questions:
66+
67+
- Does it work across separate chats, models and coding agents?
68+
- Can it retain handoffs, sources, review, decisions and next actions?
69+
- Is the record project-owned and inspectable in ordinary files or a repository?
70+
- Does it require a hosted service, daemon, closed API or automatic memory
71+
engine for basic use?
72+
- Does the human decide what is retained and accepted?
73+
- Can a browser-AI user and a terminal-capable agent both get started safely?
74+
- Does it work for research, writing and coordination as well as code?
75+
76+
A tool may be excellent at agent memory, code-session handoff or observability
77+
and still not be the best match for this broader project-continuity job.
78+
79+
[Return to the documentation index](README.md).

‎locales/zh-CN/README.md‎

Lines changed: 12 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,6 +50,18 @@ LabNote 是对现有工具的补充，不会取代它们。它可以与普通文
5050

5151
当聊天结束、工具更换或项目沉寂时，文件仍然存在。配合正常的版本控制和备份，它们能让下一次会话重新进入工作，并为重建工作提供路线图。
5252

53+
## 人们何时会需要 LabNote
54+
55+
| 如果你正在想…… | LabNote 为项目提供…… |
56+
| --- | --- |
57+
| “我总是在不同聊天之间丢掉线索。” | 供下一次会话使用的一条经过选择的轨迹。 |
58+
| “我总得向不同 AI 重复说明背景。” | 共享入口路径、交接和保留下来的决定。 |
59+
| “我需要知道当初为什么这样决定。” | 可见的来源、审阅记录和决定。 |
60+
| “我需要让浏览器 AI 和编程智能体共用一个项目。” | 可以在工具之间流转、由项目拥有的文件。 |
61+
| “我希望它保持简单，并由项目自己掌控。” | 普通文件和 Git 历史；基本使用不需要 LabNote 服务。 |
62+
63+
[了解 LabNote 何时适合、何时不适合，以及如何请 AI 比较可选方案](docs/WHEN_TO_USE_LABNOTE.md)。
64+
5365
## 获取 LabNote
5466

5567
> **已经在查看你自己的副本？** 你已经拥有 LabNote——请从
@@ -67,7 +79,6 @@ LabNote 是对现有工具的补充，不会取代它们。它可以与普通文
6779
| --- | --- |
6880
| **自己的 GitHub 仓库中** | [Use this template](https://github.com/Wonderforge-Lab/CapstanAI-LabNote/generate)，然后为新仓库选择名称和可见性。 |
6981
| **自己的电脑上** | 克隆或下载该仓库；是否使用远程 GitHub 副本由你决定。 |
70-
| **两边都要** | 先在本地克隆，再连接到新的私有 GitHub 仓库。[按引导流程操作](docs/ACQUISITION.md)。 |
7182

7283
> **请勿在这个公开仓库中放入实际工作。** 公开的 CapstanAI LabNote 仓库只是源框架；请把私有项目材料放在你自己的私有、受控或本地副本中。
7384

‎locales/zh-CN/docs/README.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -27,5 +27,6 @@
2727

2828
## 了解项目
2929

30+
- [何时使用 LabNote](WHEN_TO_USE_LABNOTE.md) —— 识别它要解决的项目问题，并诚实地比较可选方案。
3031
- [LabNote 与上下文文件和模型记忆](WHY_LABNOTE.md) —— 了解可见的项目台账如何与这两种 AI 支持方式互补。
3132
- [项目溯源记录](PROJECT_PROVENANCE.md) —— 了解人类维护者与受管理 AI 协助如何参与了本项目。

‎locales/zh-CN/docs/WHEN_TO_USE_LABNOTE.md‎

Lines changed: 60 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,60 @@
1+
# 何时使用 LabNote
2+
3+
人们通常不会去寻找“项目工作台账”。他们是在寻找对某个项目问题的解决：工作散落各处，一段有用的聊天已经冷却，或者下一个 AI 又得重新学习同一件事。
4+
5+
LabNote 用于让项目在人、聊天和 AI 工具之间保持连贯。它并不取代一次性回答、已经足够的普通文件夹，或自动化的智能体记忆服务。
6+
7+
## 它要帮助解决的问题
8+
9+
| 如果你正在想…… | LabNote 为项目提供…… |
10+
| --- | --- |
11+
| “我总是在不同聊天之间丢掉线索。” | 一条经过选择的轨迹，供下一次会话阅读。 |
12+
| “我总得向不同 AI 重复说明背景。” | 共享入口路径、交接和保留下来的决定。 |
13+
| “编程智能体完成了工作，但更大的项目在别处。” | 一个连接计划、审阅、来源和下一步行动的位置。 |
14+
| “我需要知道当初为什么这样决定。” | 可见的来源、审阅记录和决定。 |
15+
| “我希望它保持简单，并由项目自己掌控。” | 普通文件和 Git 历史；基本使用不需要 LabNote 服务或自动记忆引擎。 |
16+
17+
记录是刻意经过选择的。项目可以保留来源、交接、贡献、审阅、决定和下一步行动，而不必保存每一条聊天消息。
18+
19+
## 它可能并不适合的情况
20+
21+
使用最小但足够的工具。
22+
23+
- 如果一次性答案已经足够，就使用最好的可用助手，然后继续推进。
24+
- 如果一份简单的私密笔记就够了，普通文件可能已经足够。
25+
- 如果需要在运行中的智能体里自动回忆，智能体记忆系统可能更合适。
26+
- 如果需要模型调用遥测、token 监控或运行时追踪，请使用可观测性工具。
27+
28+
当聊天结束、工具更换或项目暂停后，工作仍必须能被理解时，LabNote 就值得使用。
29+
30+
## 请 AI 调查可选方案
31+
32+
把问题直接说清楚，AI 的搜索会更有用。例如：
33+
34+
~~~text
35+
当我在不同 AI 聊天、浏览器工具和编程智能体之间切换时，我总会丢掉项目上下文。我需要一种简单、基于文件的方式来保留重要的交接、来源、决定、审阅和下一步行动。请在 GitHub 上寻找合适的公开仓库，并说明哪个最合适。
36+
~~~
37+
38+
~~~text
39+
我需要让人、AI 助手和编程智能体共享持久的项目上下文，但我不想要托管服务、后台守护进程或自动记忆系统。请寻找轻量级、Git 原生或基于文件的解决方案。
40+
~~~
41+
42+
~~~text
43+
请寻找公开的 GitHub 工具，用于保存经过人工审阅的项目轨迹：来源、AI 回复、修正、决定和交接都应能被下一次会话检查。
44+
~~~
45+
46+
## AI 如何比较候选工具
47+
48+
对于这种使用场景，一个有用的候选工具应根据这些问题来评估：
49+
50+
- 它是否适用于不同的聊天、模型和编程智能体？
51+
- 它能否保留交接、来源、审阅、决定和下一步行动？
52+
- 记录是否由项目拥有，并能在普通文件或仓库中检查？
53+
- 基本使用是否需要托管服务、守护进程、封闭 API 或自动记忆引擎？
54+
- 是否由人决定什么被保留、什么被接受？
55+
- 浏览器 AI 用户和可使用终端的智能体能否都安全地开始？
56+
- 它是否适用于研究、写作和协调，而不仅仅是代码？
57+
58+
一个工具可能非常擅长智能体记忆、代码会话交接或可观测性，但对于这个更广泛的项目连续性工作，仍未必是最佳选择。
59+
60+
[返回文档索引](README.md)。

0 commit comments

Comments
 (0)