wenlan-mcp 0.9.0 → 0.9.2

package/README.md

@@ -25,6 +25,10 @@
   <a href="#what-you-get"><img alt="Obsidian" src="https://img.shields.io/badge/Obsidian-Markdown%20pages-7C3AED"></a>
 </p>
 
+<p align="center">
+  English | <a href="./README.zh-Hans.md">简体中文</a> | <a href="./README.zh-Hant.md">繁體中文</a>
+</p>
+
 **A living personal knowledge library for the AI-native age, built by your agents and grounded in its sources.**
 
 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.
@@ -39,9 +43,9 @@ Unlike a static llm-wiki, it keeps evolving between sessions. Unlike a black-box
 
 ## What makes Wenlan distinct
 
-1. **Evolves on its own.** Most memory tools just hand back what you put in. Wenlan keeps working between sessions: it dedupes, links, and clusters your captures into source-cited wiki pages that feed retrieval alongside the atomic notes they came from. Unlike a static llm-wiki, the library stays current without you maintaining it.
-2. **One home, locked to none.** Every MCP client queries the same local daemon, so context built in one tool shows up in the next. Obsidian is one optional view you can symlink in, not where your work lives.
-3. **Sourced, so you can trust it.** Every page cites the memories it came from, and the daemon refuses unsourced pages rather than letting hallucinated summaries in. Low-confidence captures and contradictions surface for you to confirm or correct, but the everyday flow never stops for approval. Fix something once and Wenlan supersedes the old fact instead of serving both.
+1. **Trustworthy on its own.** Every page cites the memories it came from, and the daemon refuses unsourced pages rather than letting hallucinated summaries in. It dedupes facts and supersedes the old version when one changes, so you read a clean, current wiki instead of a pile of duplicates. The everyday flow never stops for approval; a capture only surfaces for you when something genuinely conflicts.
+2. **Evolves on its own.** Most memory tools just hand back what you put in. Wenlan keeps working between sessions, clustering your captures into source-cited wiki pages that feed retrieval alongside the atomic notes they came from. Unlike a static llm-wiki, it stays current without you maintaining it.
+3. **One home, locked to none.** Every MCP client queries the same local daemon, so context built in one tool shows up in the next. Obsidian is one optional view you can symlink in, not where your work lives.
 4. **Real git versioning.** Memory, page, and session writes commit into `~/.wenlan/.git/`, so you can inspect, diff, revert, or branch the Markdown artifacts.
    ```text
    a1b2c3d page: embedding-retrieval refreshed (4 sources)
@@ -57,7 +61,7 @@ Unlike a static llm-wiki, it keeps evolving between sessions. Unlike a black-box
 
 ```text
 /plugin marketplace add 7xuanlu/claude-plugins
-/plugin install origin@7xuanlu
+/plugin install wenlan@7xuanlu
 /init
 ```
 
@@ -86,15 +90,15 @@ Set up the local Wenlan runtime:
 npx -y wenlan setup
 ```
 
-Then start with `~/.origin/bin/origin status`, `~/.origin/bin/origin recall <query>`, or `~/.origin/bin/origin store <text>`. CLI details: [crates/wenlan-cli](crates/wenlan-cli/README.md).
+Then start with `~/.wenlan/bin/wenlan status`, `~/.wenlan/bin/wenlan recall <query>`, or `~/.wenlan/bin/wenlan store <text>`. CLI details: [crates/wenlan-cli](crates/wenlan-cli/README.md).
 
 Service management:
 
 ```bash
-origin install            # register + start the daemon (stops a running one first)
-origin restart            # stop + start the daemon -- run this after upgrading
-origin status
-origin uninstall
+wenlan install            # register + start the daemon (stops a running one first)
+wenlan restart            # stop + start the daemon -- run this after upgrading
+wenlan status
+wenlan uninstall
 ```
 
 After upgrading Wenlan (`npx -y wenlan setup` or `install.sh`), the new binary is on disk but the already-running daemon keeps serving the old code until you restart it. `wenlan install` now restarts automatically; if you upgraded another way, run `wenlan restart`.
@@ -163,26 +167,25 @@ Or declaratively via `~/.wenlan/spaces.toml` (see
     wenlan space show ideas
     wenlan space move scratch career
 
-`origin doctor` prints the current resolver state so you can see exactly
+`wenlan doctor` prints the current resolver state so you can see exactly
 which layer chose the active space.
 
 ---
 
 ## Evaluation
 
-**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 below is retrieval-only, 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.
+**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.
 
-Update workflow in [docs/eval](docs/eval/README.md).
+Update workflow and answer-quality snapshots live in [docs/eval](docs/eval/README.md).
 
 
 <!-- EVAL_SNAPSHOT_START -->
 | Benchmark | Recall@5 | MRR | NDCG@10 |
 |---|---:|---:|---:|
-| LongMemEval (oracle, 500 Q) | 93.6% | 0.857 | 0.883 |
-| LoCoMo (locomo10) | 70.0% | 0.647 | 0.684 |
+| LME_Oracle (500 Q) | 93.6% | 0.857 | 0.883 |
+| LME_S (deep, 90 Q) | 87.7% | 0.815 | 0.822 |
 <!-- EVAL_SNAPSHOT_END -->
 
-
 ---
 
 ## Repo Map
@@ -233,7 +236,7 @@ Longer-form writing on AI work memory and how Wenlan compares lives at [useorigi
 **Comparisons**
 - [Wenlan vs Basic Memory](https://useorigin.app/learn/origin-vs-basic-memory): Markdown knowledge base vs AI work-session memory
 - [Wenlan vs claude-mem](https://useorigin.app/learn/origin-vs-claude-mem): observer-style Claude Code memory vs MCP-first cross-tool memory
-- [Wenlan vs Superlocal Memory](https://useorigin.app/learn/origin-vs-superlocal-memory): includes the honest LoCoMo benchmark concession
+- [Wenlan vs Superlocal Memory](https://useorigin.app/learn/origin-vs-superlocal-memory): tradeoffs against another local memory shape
 
 **Docs**
 - [Get started](https://useorigin.app/docs/get-started): install + verify the first local memory loop

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wenlan-mcp",
-  "version": "0.9.0",
+  "version": "0.9.2",
   "description": "Local-first memory layer for AI agents - MCP server",
   "keywords": [
     "mcp",
@@ -15,7 +15,7 @@
     "agents",
     "claude",
     "chatgpt",
-    "origin"
+    "wenlan"
   ],
   "homepage": "https://github.com/7xuanlu/wenlan#readme",
   "bugs": {