wenlan-mcp 0.19.2 → 0.19.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +43 -34
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -6,8 +6,8 @@
|
|
|
6
6
|
</p>
|
|
7
7
|
|
|
8
8
|
<p align="center">
|
|
9
|
-
Wenlan
|
|
10
|
-
|
|
9
|
+
Wenlan turns your scattered documents, AI chats, and coding sessions into one local wiki with citations:<br>
|
|
10
|
+
a source of truth for you and your AI tools that keeps up as they change.
|
|
11
11
|
</p>
|
|
12
12
|
|
|
13
13
|
<p align="center">
|
|
@@ -33,6 +33,18 @@ https://github.com/user-attachments/assets/5e661389-d7ea-4a36-a645-2b1ec2a92d32
|
|
|
33
33
|
|
|
34
34
|
<p>Cover: localized composite of App views with demo data; the graph is illustrative, not a native three-column layout.</p>
|
|
35
35
|
|
|
36
|
+
<a id="why-wenlan"></a>
|
|
37
|
+
|
|
38
|
+
<br>
|
|
39
|
+
|
|
40
|
+
## Why Wenlan
|
|
41
|
+
|
|
42
|
+
I started Wenlan out of anxiety about my own knowledge: notes, documents, and AI chats scattered everywhere, always changing. Keeping an Obsidian vault from rotting within three months took plugins, a workflow, and constant upkeep, and LLM-wiki setups weren't much easier day to day. I wanted an AI-native knowledge base app that stays useful without the hassle.
|
|
43
|
+
|
|
44
|
+
- **Everything in one place:** Documents, Markdown files, Obsidian vaults, web links, and exported AI chats come into one wiki.
|
|
45
|
+
- **One wiki for all your AI tools:** Claude Code, Codex, Cursor, and other MCP clients work from the same pages.
|
|
46
|
+
- **Built in, not bolted on:** Saving, organizing, citing, and updating pages live in one app, with no maze of plugins to wire up.
|
|
47
|
+
|
|
36
48
|
<a id="quickstart"></a>
|
|
37
49
|
<a id="start-in-30-seconds"></a>
|
|
38
50
|
<a id="start-with-the-app"></a>
|
|
@@ -55,8 +67,6 @@ Save your material in Wenlan so your everyday AI tools can use it to answer ques
|
|
|
55
67
|
|
|
56
68
|
Prefer the terminal? [Use Wenlan through the CLI or AI tools](docs/setup-and-data.md#installation).
|
|
57
69
|
|
|
58
|
-
Optionally enable Steep with a [local model](docs/steep.md#enable-steep) to organize memories and update knowledge pages in the background.
|
|
59
|
-
|
|
60
70
|
### 2. Create a page or import existing material
|
|
61
71
|
|
|
62
72
|
Create a page in Wenlan, connect an Obsidian vault, or import earlier AI conversations and memories. [Import guide](docs/import-guide.md).
|
|
@@ -69,32 +79,15 @@ Create a page in Wenlan, connect an Obsidian vault, or import earlier AI convers
|
|
|
69
79
|
| ChatGPT Desktop (Codex), Codex CLI | Plugin | [Codex guide](docs/setup-with-ai.md#codex) |
|
|
70
80
|
| Cursor, VS Code, Gemini CLI, Muse Code | MCP | [MCP guide](docs/setup-with-ai.md#mcp-only-setup-and-other-clients) |
|
|
71
81
|
|
|
72
|
-
After installing a plugin, start a new AI session and run `/wenlan` (`$wenlan` in Codex). It checks that Wenlan works and sets it up when needed.
|
|
82
|
+
After installing a plugin, start a new AI session and run `/wenlan` (`$wenlan` in Codex). It checks that Wenlan works and sets it up when needed.
|
|
73
83
|
|
|
74
|
-
Imported material is ready to use
|
|
84
|
+
Imported material is ready to use right away, and you can turn it into pages whenever you want. Ask your AI:
|
|
75
85
|
|
|
76
|
-
>
|
|
77
|
-
|
|
78
|
-
<a id="daily-workflow"></a>
|
|
79
|
-
|
|
80
|
-
<br>
|
|
81
|
-
|
|
82
|
-
## In everyday use
|
|
86
|
+
> /recall my earlier notes and decisions on this, then help me: …
|
|
83
87
|
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
<p align="center">
|
|
87
|
-
<img src="./docs/assets/wenlan-daily-workflow.png" alt="Sources and saved memories accumulate in Wenlan; use them in the App or AI tools, then save new memories and work progress for later." width="100%">
|
|
88
|
-
</p>
|
|
89
|
-
|
|
90
|
-
Simplified workflow. Plugin commands and page organization are optional, with no fixed sequence.
|
|
91
|
-
|
|
92
|
-
- **Work in the App.** Add material, write or edit pages, follow citations, and review proposed changes without connecting AI.
|
|
93
|
-
- **Use your knowledge and write new pages.** Ask your AI to find relevant sources and memories for the task (`/recall`). It can also write cited pages or update existing ones from their current version, then save them to Wenlan.
|
|
94
|
-
- **Keep what you learn.** Save a decision or lesson, with its reasons and sources, in the App or through your AI (`/capture`).
|
|
95
|
-
- **Pause and resume.** Save findings and a session log, update affected pages, and record progress and next steps in the project Brief (`/handoff`). Pick up that context next time (`/brief`).
|
|
88
|
+
In Codex, use `$recall`. With an MCP-only tool, just ask: “Check Wenlan for my earlier notes and decisions on this, then help me: …”
|
|
96
89
|
|
|
97
|
-
|
|
90
|
+
Later, you can turn on [Steep](#steep-keep-knowledge-useful-as-it-changes) with a [local model](docs/steep.md#enable-steep) to organize memories and update pages in the background.
|
|
98
91
|
|
|
99
92
|
<a id="what-does-wenlan-build"></a>
|
|
100
93
|
<a id="why-it-compounds"></a>
|
|
@@ -137,6 +130,27 @@ Scanned PDFs need text extraction first; chat attachments are not imported. [Imp
|
|
|
137
130
|
</p>
|
|
138
131
|
<p>App nodes and connections; translated labels and illustrative regions.</p>
|
|
139
132
|
|
|
133
|
+
<a id="daily-workflow"></a>
|
|
134
|
+
|
|
135
|
+
<br>
|
|
136
|
+
|
|
137
|
+
## In everyday use
|
|
138
|
+
|
|
139
|
+
Save new findings and progress as you work, then pick up where you left off next time.
|
|
140
|
+
|
|
141
|
+
<p align="center">
|
|
142
|
+
<img src="./docs/assets/wenlan-daily-workflow.png" alt="Sources and saved memories accumulate in Wenlan; use them in the App or AI tools, then save new memories and work progress for later." width="100%">
|
|
143
|
+
</p>
|
|
144
|
+
|
|
145
|
+
Simplified workflow. Plugin commands and page organization are optional, with no fixed sequence.
|
|
146
|
+
|
|
147
|
+
- **Work in the App.** Add material, write or edit pages, follow citations, and review proposed changes without connecting AI.
|
|
148
|
+
- **Use your knowledge and write new pages.** Ask your AI to find relevant sources and memories for the task (`/recall`). It can also write cited pages or update existing ones from their current version, then save them to Wenlan.
|
|
149
|
+
- **Keep what you learn.** Save a decision or lesson, with its reasons and sources, in the App or through your AI (`/capture`).
|
|
150
|
+
- **Pause and resume.** Save findings and a session log, update affected pages, and record progress and next steps in the project Brief (`/handoff`). Pick up that context next time (`/brief`).
|
|
151
|
+
|
|
152
|
+
**Organize accumulated memories when needed:** Synthesize or refresh cited pages from related memories (`/wenlan distill`); writing a new page does not require this step. [Plugin commands](plugin/skills/README.md).
|
|
153
|
+
|
|
140
154
|
<a id="how-wenlan-works"></a>
|
|
141
155
|
<a id="how-does-it-work"></a>
|
|
142
156
|
|
|
@@ -150,7 +164,7 @@ Scanned PDFs need text extraction first; chat attachments are not imported. [Imp
|
|
|
150
164
|
|
|
151
165
|
## Put your knowledge to work with AI
|
|
152
166
|
|
|
153
|
-
|
|
167
|
+
Once your material is in Wenlan, your AI tools can build on it: retrieve earlier decisions with their supporting material, save new work, and keep using it as the evidence changes.
|
|
154
168
|
|
|
155
169
|
**Use it for:**
|
|
156
170
|
|
|
@@ -166,12 +180,7 @@ An agent can read files and write text. Wenlan adds a **shared knowledge base ma
|
|
|
166
180
|
|
|
167
181
|
**Coming soon:** Coding repository support in Spaces.
|
|
168
182
|
|
|
169
|
-
|
|
170
|
-
<img src="./docs/assets/wenlan-knowledge-to-work.png" alt="Let AI continue from what you already know: keyword, semantic and Graph retrieval" width="100%">
|
|
171
|
-
</p>
|
|
172
|
-
<p>Fictional example, not a product test; Wenlan adds context alongside Claude’s native memory.</p>
|
|
173
|
-
|
|
174
|
-
Turn on **Web access** in Settings to let supported web AI clients such as Claude, ChatGPT, or Muse search your library or a chosen Space while your computer is online. This feature is experimental; queries and results pass through a relay. See the [privacy limits](docs/PRIVACY.md#pre-release-standalone-wenlan-relay-connector).
|
|
183
|
+
Turn on **Web access** in Settings to let supported web AI clients such as Claude, ChatGPT, or Muse search your library or a chosen Space while your computer is online. When you allow an app, choose search only or search and write; a write app can also add, edit and delete, and AI apps can ask you before each change. This feature is experimental; queries and results pass through a relay. See the [privacy limits](docs/PRIVACY.md#pre-release-standalone-wenlan-relay-connector).
|
|
175
184
|
|
|
176
185
|
<a id="what-makes-wenlan-distinct"></a>
|
|
177
186
|
<a id="why-is-wenlan-different"></a>
|
|
@@ -197,7 +206,7 @@ Saving material is only the start. **Steep prepares it for reuse and keeps suppo
|
|
|
197
206
|
[Steep guide: triggers, review rules, and model setup](docs/steep.md). Choose an on-device model, a local server, or a cloud provider; model-backed background work is optional.
|
|
198
207
|
|
|
199
208
|
<p align="center">
|
|
200
|
-
<img src="./docs/assets/wenlan-updates-history.png" alt="Illustrative flow: a finding in a source document updates memory from V1 to V2, then informs a
|
|
209
|
+
<img src="./docs/assets/wenlan-updates-history.png" alt="Illustrative flow: a finding in a source document updates memory from V1 to V2, then informs a page that is either updated automatically or sent for review." width="100%">
|
|
201
210
|
</p>
|
|
202
211
|
<p>Illustration based on current update behavior; not an App screenshot.</p>
|
|
203
212
|
|