diff --git a/README.md b/README.md
index 136dbc2a7..fc5bf326d 100644
--- a/README.md
+++ b/README.md
@@ -47,9 +47,8 @@ Your lobsters and Hermes Agents now have **the best** memory system โ choose *
| ๐ Plugin |
๐ก Core Features
| ๐งฉ Resources |
| :----: | :--- | :---: |
-| ๐ง๐ป [**Hermes Agent Local Plugin**](https://x.com/MemOS_dev/status/2043400241232458204) | - Visual Management via Web UI.
- 100% local, Hybrid retrieval, Smart dedup,
Skill evolution, Multi-Agent knowledge hub.
| ๐ [Docs](https://memos-docs.openmem.net/cn/openclaw/hermes_local_plugin) ยท ๐ [GitHub](https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-plugin) |
+| ๐ง [**memos-local-plugin 2.0**](https://github.com/hijzy/MemOS/tree/main/apps/memos-local-plugin) | - One local-first memory core for **Hermes Agent** and **OpenClaw**.
- Self-evolving memory: L1 trace, L2 policy, L3 world model,
and crystallized Skills driven by feedback.
| ๐ [GitHub](https://github.com/hijzy/MemOS/tree/main/apps/memos-local-plugin) ยท ๐ฆ [NPM](https://www.npmjs.com/package/@memtensor/memos-local-plugin) |
| โ๏ธ [**OpenClaw Cloud Plugin**](https://x.com/MemOS_dev/status/2019254160919769171?s=20) | - [Reduces token usage by 72%.](https://x.com/MemOS_dev/status/2020854044583924111)
- [Multi-agent memory sharing by `user_id`.](https://x.com/MemOS_dev/status/2020538135487062094)
| ๐ฅ๏ธ [MemOS Dashboard](https://memos-dashboard.openmem.net/login/) ยท ๐ [Full Tutorial](https://memos-docs.openmem.net/openclaw/guide#_4-update-plugin) |
-| ๐ฆ [**OpenClaw Local Plugin**](https://x.com/MemOS_dev/status/2031342078480019505) | - 0 cloud dependency by local SQLite.
- FTS5 + vector search, Task auto-summarization,
Multi-Agent memory isolation & skill sharing.
| ๐ [Homepage](https://memos-claw.openmem.net) ยท ๐ [Docs](https://memos-claw.openmem.net/docs) ยท ๐ฆ [NPM](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin) |
@@ -70,9 +69,12 @@ Your lobsters and Hermes Agents now have **the best** memory system โ choose *
### News
+- **2026-05-09** ยท ๐ง **memos-local-plugin 2.0**
+ Official local memory plugin for **Hermes Agent** and **OpenClaw**. One core powers self-evolving memory across L1 traces, L2 policies, L3 world models, and crystallized Skills, with local-first storage and feedback-driven retrieval.
+
- **2026-04-10** ยท ๐ง๐ป **MemOS Hermes Agent Local Plugin**
Official Hermes Agent memory plugins launched: Hybrid retrieval (FTS5 + vector), smart dedup, tiered skill evolution, multi-agent collaboration. 100% local, zero cloud dependency.
-
+
- **2026-03-08** ยท ๐ฆ **MemOS OpenClaw Plugin โ Cloud & Local**
Official OpenClaw memory plugins launched. **Cloud Plugin**: hosted memory service with 72% lower token usage and multi-agent memory sharing ([MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin)). **Local Plugin** (`v1.0.0`): 100% on-device memory with persistent SQLite, hybrid search (FTS5 + vector), task summarization & skill evolution, multi-agent collaboration, and a full Memory Viewer dashboard.