diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9747d327fc0..65b7b72d1f5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,7 +6,8 @@ Docs: https://docs.openclaw.ai
 
 ### Changes
 
-- Agents/local models: add `agents.defaults.localModelMode: "lean"` to drop heavyweight default tools like `browser`, `cron`, and `message`, reducing prompt size for weaker local-model setups without changing the normal path. Thanks @ImLukeF.
+- Docs/showcase: add a scannable hero, complete section jump links, and a responsive video grid for community examples. (#48493) Thanks @jchopard69.
+- Agents/local models: add experimental `agents.defaults.experimental.localModelLean: true` to drop heavyweight default tools like `browser`, `cron`, and `message`, reducing prompt size for weaker local-model setups without changing the normal path. Thanks @ImLukeF.
 - QA/Matrix: split Matrix live QA into a source-linked `qa-matrix` runner and keep repo-private `qa-*` surfaces out of packaged and published builds. (#66723) Thanks @gumadeiras.
 - Control UI/Overview: add a Model Auth status card showing OAuth token health and provider rate-limit pressure at a glance, with attention callouts when OAuth tokens are expiring or expired. Backed by a new `models.authStatus` gateway method that strips credentials and caches for 60s. (#66211) Thanks @omarshahine.
 - GitHub Copilot/memory search: add a GitHub Copilot embedding provider for memory search, and expose a dedicated Copilot embedding host helper so plugins can reuse the transport while honoring remote overrides, token refresh, and safer payload validation. (#61718) Thanks @feiskyer and @vincentkoc.
diff --git a/docs/.generated/config-baseline.sha256 b/docs/.generated/config-baseline.sha256
index 32d8fec82de..47d84462069 100644
--- a/docs/.generated/config-baseline.sha256
+++ b/docs/.generated/config-baseline.sha256
@@ -1,4 +1,4 @@
-8ae312a03361238f30a2454258808744b7ad6a5d079ff321eaa60f4b8af82005  config-baseline.json
-2dac6cea7a03051e10c4f1ceeb8025c23220a550b940156d6eddeb8e3ecd75f1  config-baseline.core.json
+900c26a9b060f1dfa712abfba877bd3bf9c7b0c9f2294faf9834038283ec24b6  config-baseline.json
+d956a1d60f776bba712cb04374a4f5657cad95bb088b536c5e3e4e29d4a21328  config-baseline.core.json
 ef83a06633fc001b5b2535566939186ecb49d05cd1a90b40e54cc58d3e6e44e3  config-baseline.channel.json
 5f5d4e850df6e9854a85b5d008236854ce185c707fdbb566efcf00f8c08b36e3  config-baseline.plugin.json
diff --git a/docs/gateway/local-models.md b/docs/gateway/local-models.md
index c54e2165c0e..28b1c2a12d7 100644
--- a/docs/gateway/local-models.md
+++ b/docs/gateway/local-models.md
@@ -165,8 +165,9 @@ Compatibility notes for stricter OpenAI-compatible backends:
   agent-runtime prompt shape, especially when tool schemas are included. If the
   backend works for tiny direct `/v1/chat/completions` calls but fails on normal
   OpenClaw agent turns, first try
-  `agents.defaults.localModelMode: "lean"` to drop heavyweight default tools
-  like `browser`, `cron`, and `message`; if that still fails, try
+  `agents.defaults.experimental.localModelLean: true` to drop heavyweight
+  default tools like `browser`, `cron`, and `message`; this is an experimental
+  flag, not a stable default-mode setting. If that still fails, try
   `models.providers.<provider>.models[].compat.supportsTools: false`.
 - If the backend still fails only on larger OpenClaw runs, the remaining issue
   is usually upstream model/server capacity or a backend bug, not OpenClaw's
diff --git a/src/agents/pi-tools.model-provider-collision.test.ts b/src/agents/pi-tools.model-provider-collision.test.ts
index c04f8a8e6fb..e29b482f657 100644
--- a/src/agents/pi-tools.model-provider-collision.test.ts
+++ b/src/agents/pi-tools.model-provider-collision.test.ts
@@ -116,7 +116,7 @@ describe("applyModelProviderToolPolicy", () => {
     expect(toolNames(filtered)).toEqual(["read", "web_search", "exec"]);
   });
 
-  it("drops heavyweight tools when lean local-model mode is enabled", () => {
+  it("drops heavyweight tools when the experimental lean local-model flag is enabled", () => {
     const filtered = __testing.applyModelProviderToolPolicy(
       [
         { name: "read" },
@@ -129,7 +129,9 @@ describe("applyModelProviderToolPolicy", () => {
         config: {
           agents: {
             defaults: {
-              localModelMode: "lean",
+              experimental: {
+                localModelLean: true,
+              },
             },
           },
         },
@@ -142,7 +144,7 @@ describe("applyModelProviderToolPolicy", () => {
     expect(toolNames(filtered)).toEqual(["read", "exec"]);
   });
 
-  it("keeps heavyweight tools when lean local-model mode is not enabled", () => {
+  it("keeps heavyweight tools when the experimental lean local-model flag is not enabled", () => {
     const filtered = __testing.applyModelProviderToolPolicy(
       [
         { name: "read" },
@@ -155,7 +157,9 @@ describe("applyModelProviderToolPolicy", () => {
         config: {
           agents: {
             defaults: {
-              localModelMode: "default",
+              experimental: {
+                localModelLean: false,
+              },
             },
           },
         },
diff --git a/src/agents/pi-tools.ts b/src/agents/pi-tools.ts
index 4a1679c70e9..a3f79754da0 100644
--- a/src/agents/pi-tools.ts
+++ b/src/agents/pi-tools.ts
@@ -131,7 +131,7 @@ function applyModelProviderToolPolicy(
     modelCompat?: ModelCompatConfig;
   },
 ): AnyAgentTool[] {
-  if (params?.config?.agents?.defaults?.localModelMode === "lean") {
+  if (params?.config?.agents?.defaults?.experimental?.localModelLean === true) {
     const leanDeny = new Set(["browser", "cron", "message"]);
     tools = tools.filter((tool) => !leanDeny.has(tool.name));
   }
diff --git a/src/config/schema.base.generated.ts b/src/config/schema.base.generated.ts
index 2da7b522cd9..f009aee0807 100644
--- a/src/config/schema.base.generated.ts
+++ b/src/config/schema.base.generated.ts
@@ -3243,20 +3243,20 @@ export const GENERATED_BASE_CONFIG_SCHEMA: BaseConfigSchemaResponse = {
                 description:
                   "Max total characters across all injected workspace bootstrap files (default: 150000).",
               },
-              localModelMode: {
-                anyOf: [
-                  {
-                    type: "string",
-                    const: "default",
+              experimental: {
+                type: "object",
+                properties: {
+                  localModelLean: {
+                    type: "boolean",
+                    title: "Enable Lean Local Model Mode (Experimental)",
+                    description:
+                      "Experimental local-model prompt trim. When enabled, OpenClaw drops heavyweight default tools like browser, cron, and message for weaker or smaller local-model backends.",
                   },
-                  {
-                    type: "string",
-                    const: "lean",
-                  },
-                ],
-                title: "Local Model Mode",
+                },
+                additionalProperties: false,
+                title: "Experimental Agent Flags",
                 description:
-                  'Local-model prompt profile: "default" keeps the standard tool surface, while "lean" drops heavyweight non-essential tools for smaller or weaker models.',
+                  "Experimental agent-default flags. Keep these off unless you are intentionally testing a preview surface.",
               },
               bootstrapPromptTruncationWarning: {
                 anyOf: [
@@ -24528,10 +24528,15 @@ export const GENERATED_BASE_CONFIG_SCHEMA: BaseConfigSchemaResponse = {
       help: "Max total characters across all injected workspace bootstrap files (default: 150000).",
       tags: ["performance"],
     },
-    "agents.defaults.localModelMode": {
-      label: "Local Model Mode",
-      help: 'Local-model prompt profile: "default" keeps the standard tool surface, while "lean" drops heavyweight non-essential tools for smaller or weaker models.',
-      tags: ["advanced"],
+    "agents.defaults.experimental": {
+      label: "Experimental Agent Flags",
+      help: "Experimental agent-default flags. Keep these off unless you are intentionally testing a preview surface.",
+      tags: ["security", "advanced"],
+    },
+    "agents.defaults.experimental.localModelLean": {
+      label: "Enable Lean Local Model Mode (Experimental)",
+      help: "Experimental local-model prompt trim. When enabled, OpenClaw drops heavyweight default tools like browser, cron, and message for weaker or smaller local-model backends.",
+      tags: ["security", "advanced"],
     },
     "agents.defaults.bootstrapPromptTruncationWarning": {
       label: "Bootstrap Prompt Truncation Warning",
diff --git a/src/config/schema.help.ts b/src/config/schema.help.ts
index 9534dfe208b..c138a5fb064 100644
--- a/src/config/schema.help.ts
+++ b/src/config/schema.help.ts
@@ -848,8 +848,10 @@ export const FIELD_HELP: Record<string, string> = {
     "Max characters of each workspace bootstrap file injected into the system prompt before truncation (default: 20000).",
   "agents.defaults.bootstrapTotalMaxChars":
     "Max total characters across all injected workspace bootstrap files (default: 150000).",
-  "agents.defaults.localModelMode":
-    'Local-model prompt profile: "default" keeps the standard tool surface, while "lean" drops heavyweight non-essential tools for smaller or weaker models.',
+  "agents.defaults.experimental":
+    "Experimental agent-default flags. Keep these off unless you are intentionally testing a preview surface.",
+  "agents.defaults.experimental.localModelLean":
+    "Experimental local-model prompt trim. When enabled, OpenClaw drops heavyweight default tools like browser, cron, and message for weaker or smaller local-model backends.",
   "agents.defaults.bootstrapPromptTruncationWarning":
     'Inject agent-visible warning text when bootstrap files are truncated: "off", "once" (default), or "always".',
   "agents.defaults.startupContext":
diff --git a/src/config/schema.labels.ts b/src/config/schema.labels.ts
index 89ae176cf77..8f1b63c9bf4 100644
--- a/src/config/schema.labels.ts
+++ b/src/config/schema.labels.ts
@@ -343,7 +343,8 @@ export const FIELD_LABELS: Record<string, string> = {
   "agents.defaults.contextInjection": "Context Injection",
   "agents.defaults.bootstrapMaxChars": "Bootstrap Max Chars",
   "agents.defaults.bootstrapTotalMaxChars": "Bootstrap Total Max Chars",
-  "agents.defaults.localModelMode": "Local Model Mode",
+  "agents.defaults.experimental": "Experimental Agent Flags",
+  "agents.defaults.experimental.localModelLean": "Enable Lean Local Model Mode (Experimental)",
   "agents.defaults.bootstrapPromptTruncationWarning": "Bootstrap Prompt Truncation Warning",
   "agents.defaults.startupContext": "Startup Context",
   "agents.defaults.startupContext.enabled": "Enable Startup Context",
diff --git a/src/config/types.agent-defaults.ts b/src/config/types.agent-defaults.ts
index 005ae3feab6..4e7b53c01bb 100644
--- a/src/config/types.agent-defaults.ts
+++ b/src/config/types.agent-defaults.ts
@@ -13,7 +13,6 @@ import type { MemorySearchConfig } from "./types.tools.js";
 
 export type AgentContextInjection = "always" | "continuation-skip";
 export type EmbeddedPiExecutionContract = "default" | "strict-agentic";
-export type LocalModelMode = "default" | "lean";
 
 export type AgentModelEntryConfig = {
   alias?: string;
@@ -199,12 +198,14 @@ export type AgentDefaultsConfig = {
   bootstrapMaxChars?: number;
   /** Max total chars across all injected bootstrap files (default: 150000). */
   bootstrapTotalMaxChars?: number;
-  /**
-   * Optional local-model prompt profile:
-   * - default: keep the standard tool surface
-   * - lean: drop heavyweight non-essential tools for smaller or weaker models
-   */
-  localModelMode?: LocalModelMode;
+  /** Experimental agent-default flags. Keep off unless you are intentionally testing a preview surface. */
+  experimental?: {
+    /**
+     * Drop heavyweight non-essential default tools for weaker or smaller local
+     * model backends. Experimental preview only.
+     */
+    localModelLean?: boolean;
+  };
   /**
    * Agent-visible bootstrap truncation warning mode:
    * - off: do not inject warning text
diff --git a/src/config/zod-schema.agent-defaults.test.ts b/src/config/zod-schema.agent-defaults.test.ts
index 62f99649bcc..7a193ffccbe 100644
--- a/src/config/zod-schema.agent-defaults.test.ts
+++ b/src/config/zod-schema.agent-defaults.test.ts
@@ -32,6 +32,15 @@ describe("agent defaults schema", () => {
     ).not.toThrow();
   });
 
+  it("accepts experimental.localModelLean", () => {
+    const result = AgentDefaultsSchema.parse({
+      experimental: {
+        localModelLean: true,
+      },
+    })!;
+    expect(result.experimental?.localModelLean).toBe(true);
+  });
+
   it("accepts contextInjection: always", () => {
     const result = AgentDefaultsSchema.parse({ contextInjection: "always" })!;
     expect(result.contextInjection).toBe("always");
diff --git a/src/config/zod-schema.agent-defaults.ts b/src/config/zod-schema.agent-defaults.ts
index 5ed294f6c2c..cf4e07c3400 100644
--- a/src/config/zod-schema.agent-defaults.ts
+++ b/src/config/zod-schema.agent-defaults.ts
@@ -52,7 +52,12 @@ export const AgentDefaultsSchema = z
     contextInjection: z.union([z.literal("always"), z.literal("continuation-skip")]).optional(),
     bootstrapMaxChars: z.number().int().positive().optional(),
     bootstrapTotalMaxChars: z.number().int().positive().optional(),
-    localModelMode: z.union([z.literal("default"), z.literal("lean")]).optional(),
+    experimental: z
+      .object({
+        localModelLean: z.boolean().optional(),
+      })
+      .strict()
+      .optional(),
     bootstrapPromptTruncationWarning: z
       .union([z.literal("off"), z.literal("once"), z.literal("always")])
       .optional(),