wenlan-mcp 0.9.1 → 0.9.3
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 +9 -6
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -25,6 +25,10 @@
|
|
|
25
25
|
<a href="#what-you-get"><img alt="Obsidian" src="https://img.shields.io/badge/Obsidian-Markdown%20pages-7C3AED"></a>
|
|
26
26
|
</p>
|
|
27
27
|
|
|
28
|
+
<p align="center">
|
|
29
|
+
English | <a href="./README.zh-Hans.md">简体中文</a> | <a href="./README.zh-Hant.md">繁體中文</a>
|
|
30
|
+
</p>
|
|
31
|
+
|
|
28
32
|
**A living personal knowledge library for the AI-native age, built by your agents and grounded in its sources.**
|
|
29
33
|
|
|
30
34
|
Wenlan (文瀾) takes its name from an imperial library that held one of China's largest book collections. Your agents capture what they learn as they work, and you add the pages and sources you already trust, so the library grows from the bottom up and the top down. Wenlan keeps it current on its own, distilling both into source-cited wiki pages.
|
|
@@ -170,19 +174,18 @@ which layer chose the active space.
|
|
|
170
174
|
|
|
171
175
|
## Evaluation
|
|
172
176
|
|
|
173
|
-
**Hybrid retrieval, transparent eval.** BGE-Base-EN-v1.5-Q + FTS5 + Reciprocal Rank Fusion; local BGE-Reranker-Base cross-encoder rerank is the default path when enabled, with BGE-Reranker-V2-M3 available as a higher-quality option. The table
|
|
177
|
+
**Hybrid retrieval, transparent eval.** BGE-Base-EN-v1.5-Q + FTS5 + Reciprocal Rank Fusion; local BGE-Reranker-Base cross-encoder rerank is the default path when enabled, with BGE-Reranker-V2-M3 available as a higher-quality option. The retrieval table is not end-to-end answer quality. ~168 tokens per recall query. Eval harness at [`crates/wenlan-core/src/eval/`](crates/wenlan-core/src/eval/). Run it yourself.
|
|
174
178
|
|
|
175
|
-
Update workflow in [docs/eval](docs/eval/README.md).
|
|
179
|
+
Update workflow and answer-quality snapshots live in [docs/eval](docs/eval/README.md).
|
|
176
180
|
|
|
177
181
|
|
|
178
182
|
<!-- EVAL_SNAPSHOT_START -->
|
|
179
183
|
| Benchmark | Recall@5 | MRR | NDCG@10 |
|
|
180
184
|
|---|---:|---:|---:|
|
|
181
|
-
|
|
|
182
|
-
|
|
|
185
|
+
| LME_Oracle (500 Q) | 93.6% | 0.857 | 0.883 |
|
|
186
|
+
| LME_S (deep, 90 Q) | 87.7% | 0.815 | 0.822 |
|
|
183
187
|
<!-- EVAL_SNAPSHOT_END -->
|
|
184
188
|
|
|
185
|
-
|
|
186
189
|
---
|
|
187
190
|
|
|
188
191
|
## Repo Map
|
|
@@ -233,7 +236,7 @@ Longer-form writing on AI work memory and how Wenlan compares lives at [useorigi
|
|
|
233
236
|
**Comparisons**
|
|
234
237
|
- [Wenlan vs Basic Memory](https://useorigin.app/learn/origin-vs-basic-memory): Markdown knowledge base vs AI work-session memory
|
|
235
238
|
- [Wenlan vs claude-mem](https://useorigin.app/learn/origin-vs-claude-mem): observer-style Claude Code memory vs MCP-first cross-tool memory
|
|
236
|
-
- [Wenlan vs Superlocal Memory](https://useorigin.app/learn/origin-vs-superlocal-memory):
|
|
239
|
+
- [Wenlan vs Superlocal Memory](https://useorigin.app/learn/origin-vs-superlocal-memory): tradeoffs against another local memory shape
|
|
237
240
|
|
|
238
241
|
**Docs**
|
|
239
242
|
- [Get started](https://useorigin.app/docs/get-started): install + verify the first local memory loop
|