diff --git a/README.md b/README.md index 97cbc755..2877390a 100644 --- a/README.md +++ b/README.md @@ -49,7 +49,7 @@ users retain control of the durable files. ## 📰 Latest Updates -- [2026.09] - **[Add Tags to Memory](https://reme.agentscope.io/en/blog_20260920) published**: an introduction +- [2026.09] - **[ReMe Memory Tags](https://reme.agentscope.io/en/blog_20260920) published**: an introduction to file-native entity tags, rebuildable tag indexes, and tag-filtered memory search. - [2026.09] - **[Hermes Agent memory provider](integrations/hermes_agent/README.md) available**: choose HTTP or embedded mode for automatic recall before model calls and asynchronous `auto_memory` after completed turns. The integration diff --git a/docs/en/blog_20260920.md b/docs/en/blog_20260920.md index dc633458..1447ade6 100644 --- a/docs/en/blog_20260920.md +++ b/docs/en/blog_20260920.md @@ -1,4 +1,4 @@ -# Add Tags to Memory +# ReMe Memory Tags Any memory system used over the long term eventually runs into a deceptively simple problem: **as memories accumulate, how do you search only the right subset?** diff --git a/github-pages/scripts/verify-build.mjs b/github-pages/scripts/verify-build.mjs index c109ca37..0da9c24b 100644 --- a/github-pages/scripts/verify-build.mjs +++ b/github-pages/scripts/verify-build.mjs @@ -104,7 +104,7 @@ assert.match( ); const EnglishBlog = await readFile(path.join(outputDir, "en/blog_20260920.html"), "utf8"); -assert.match(EnglishBlog, /