diff --git a/docs/concepts/memory-builtin.md b/docs/concepts/memory-builtin.md
index a19ac7a2c90..602f1f8b74d 100644
--- a/docs/concepts/memory-builtin.md
+++ b/docs/concepts/memory-builtin.md
@@ -38,6 +38,25 @@ To set a provider explicitly:
 
 Without an embedding provider, only keyword search is available.
 
+To force the built-in local embedding provider, point `local.modelPath` at a
+GGUF file:
+
+```json5
+{
+  agents: {
+    defaults: {
+      memorySearch: {
+        provider: "local",
+        fallback: "none",
+        local: {
+          modelPath: "~/.node-llama-cpp/models/embeddinggemma-300m-qat-Q8_0.gguf",
+        },
+      },
+    },
+  },
+}
+```
+
 ## Supported embedding providers
 
 | Provider | ID        | Auto-detected | Notes                               |
@@ -89,6 +108,17 @@ automatic user modeling.
 **Memory search disabled?** Check `openclaw memory status`. If no provider is
 detected, set one explicitly or add an API key.
 
+**Local provider not detected?** Confirm the local path exists and run:
+
+```bash
+openclaw memory status --deep --agent main
+openclaw memory index --force --agent main
+```
+
+Both standalone CLI commands and the Gateway use the same `local` provider id.
+If the provider is set to `auto`, local embeddings are considered first only
+when `memorySearch.local.modelPath` points to an existing local file.
+
 **Stale results?** Run `openclaw memory index --force` to rebuild. The watcher
 may miss changes in rare edge cases.
 
diff --git a/docs/plugins/manifest.md b/docs/plugins/manifest.md
index b6c7ed678ca..06834714714 100644
--- a/docs/plugins/manifest.md
+++ b/docs/plugins/manifest.md
@@ -370,6 +370,7 @@ read without importing the plugin runtime.
     "speechProviders": ["openai"],
     "realtimeTranscriptionProviders": ["openai"],
     "realtimeVoiceProviders": ["openai"],
+    "memoryEmbeddingProviders": ["local"],
     "mediaUnderstandingProviders": ["openai", "openai-codex"],
     "imageGenerationProviders": ["openai"],
     "videoGenerationProviders": ["qwen"],
@@ -389,6 +390,7 @@ Each list is optional:
 | `speechProviders`                | `string[]` | Speech provider ids this plugin owns.                             |
 | `realtimeTranscriptionProviders` | `string[]` | Realtime-transcription provider ids this plugin owns.             |
 | `realtimeVoiceProviders`         | `string[]` | Realtime-voice provider ids this plugin owns.                     |
+| `memoryEmbeddingProviders`       | `string[]` | Memory embedding provider ids this plugin owns.                   |
 | `mediaUnderstandingProviders`    | `string[]` | Media-understanding provider ids this plugin owns.                |
 | `imageGenerationProviders`       | `string[]` | Image-generation provider ids this plugin owns.                   |
 | `videoGenerationProviders`       | `string[]` | Video-generation provider ids this plugin owns.                   |
@@ -401,6 +403,12 @@ Provider plugins that implement `resolveExternalAuthProfiles` should declare
 through a deprecated compatibility fallback, but that fallback is slower and
 will be removed after the migration window.
 
+Bundled memory embedding providers should declare
+`contracts.memoryEmbeddingProviders` for every adapter id they expose, including
+built-in adapters such as `local`. Standalone CLI paths use this manifest
+contract to load only the owning plugin before the full Gateway runtime has
+registered providers.
+
 ## mediaUnderstandingProviderMetadata reference
 
 Use `mediaUnderstandingProviderMetadata` when a media-understanding provider has
diff --git a/docs/reference/memory-config.md b/docs/reference/memory-config.md
index 9dd7fbfa56a..8c8f912024b 100644
--- a/docs/reference/memory-config.md
+++ b/docs/reference/memory-config.md
@@ -207,6 +207,18 @@ arn:aws:bedrock:*::foundation-model/amazon.titan-embed-text-v2:0
 Default model: `embeddinggemma-300m-qat-Q8_0.gguf` (~0.6 GB, auto-downloaded).
 Requires native build: `pnpm approve-builds` then `pnpm rebuild node-llama-cpp`.
 
+Use the standalone CLI to verify the same provider path the Gateway uses:
+
+```bash
+openclaw memory status --deep --agent main
+openclaw memory index --force --agent main
+```
+
+If `provider` is `auto`, `local` is selected only when `local.modelPath` points
+to an existing local file. `hf:` and HTTP(S) model references can still be used
+explicitly with `provider: "local"`, but they do not make `auto` select local
+before the model is available on disk.
+
 ---
 
 ## Hybrid search config