feat(minimax-mem0): App (OAuth Connector) submission form

Mem0's authenticated MCP is integrated via MiniMax's Connector (like EverMe),
giving a one-click Connect UX instead of a manual API key. Uses the MiniMax
.minimax-plugin/ submission format with apps:[mem0.app.json].

mem0.app.json provider is a placeholder until MiniMax completes Connector
integration and assigns one; mem0's OAuth MCP is already fully compliant
(streamable-http, Auth Code + PKCE S256, refresh tokens, DCR).

integrations/minimax-mem0/.minimax-plugin/plugin.json

@@ -0,0 +1,18 @@
+{
+  "schemaVersion": 1,
+  "name": "mem0",
+  "displayName": "Mem0 Memory",
+  "version": "0.1.0",
+  "description": "Persistent long-term memory for your agent: remember preferences, decisions, and project context across sessions, and recall them on demand.",
+  "author": "Mem0",
+  "icon": "icon.png",
+  "category": "Productivity",
+  "exampleQueries": [
+    "Remember that I prefer TypeScript and pnpm",
+    "What do you remember about my project?",
+    "Update what you know about my deployment setup"
+  ],
+  "apps": ["mem0.app.json"],
+  "mcpServers": [],
+  "skills": ["skills/memory/SKILL.md"]
+}

integrations/minimax-mem0/README.md

@@ -8,23 +8,26 @@ It gives a MiniMax agent persistent long-term memory: it remembers the user's pr
 
 This is a declarative MiniMax plugin (no build step). It follows the MiniMax plugin spec:
 
-Built to the [Agent Plugins 1.0](https://agent-plugins.org/specification) standard, which the MiniMax runtime imports and validates against.
+Built as a MiniMax **App** (OAuth connect), the same one-click "Connect" experience as peer memory plugins. Mem0's authenticated MCP server is integrated through MiniMax's Connector, so users authorize their Mem0 account once and never handle a key.
 
 ```
 minimax-mem0/
-  plugin.json            # manifest (Agent Plugins 1.0, at plugin root)
-  mcp.json               # remote MCP: https://mcp.mem0.ai/mcp/ (auto-discovered at root)
+  .minimax-plugin/
+    plugin.json          # manifest: apps + skills
+  mem0.app.json          # App capability -> Connector provider (assigned by MiniMax)
   icon.png               # square Mem0 icon
   skills/
     memory/
       SKILL.md           # when to recall / save / update memory
 ```
 
-Two capabilities:
+Capabilities:
 
-- **MCP** (`mcp.json`) points at Mem0's hosted MCP server (`https://mcp.mem0.ai/mcp/`), which exposes the memory tools (`add_memory`, `search_memories`, `update_memory`, `delete_memory`, and more). No secrets are stored in the package.
+- **App** (`mem0.app.json`) connects the agent to Mem0's OAuth-secured MCP server through MiniMax's Connector (tools: `add_memory`, `search_memories`, `update_memory`, `delete_memory`, and more). The user clicks Connect, authorizes their Mem0 account, done. No secrets in the package.
 - **Skill** (`skills/memory/SKILL.md`) tells the agent when to search, save, update, and delete memory so recall happens automatically.
 
+> **Pending:** the App `provider` in `mem0.app.json` is assigned by MiniMax once they complete Connector integration for Mem0's OAuth MCP server. It is a placeholder until then.
+
 ## Authentication
 
 Mem0's MCP server requires authentication. Per the MiniMax plugin spec, no credentials are placed in this package; the MiniMax client authorizes the user's Mem0 account through the MCP OAuth flow on first use. Users get a Mem0 account from the [Mem0 dashboard](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=integration-minimax).

integrations/minimax-mem0/mcp.json

@@ -1,9 +0,0 @@
-{
-  "$schema": "https://agent-plugins.org/schemas/1.0.0/mcp.schema.json",
-  "mcpServers": {
-    "mem0": {
-      "type": "streamable-http",
-      "url": "https://mcp.mem0.ai/mcp/"
-    }
-  }
-}

integrations/minimax-mem0/mem0.app.json

@@ -0,0 +1,4 @@
+{
+  "schemaVersion": 1,
+  "provider": "PENDING_MINIMAX_CONNECTOR"
+}

integrations/minimax-mem0/plugin.json

@@ -1,11 +0,0 @@
-{
-  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
-  "name": "mem0",
-  "version": "0.1.0",
-  "description": "Persistent long-term memory for your agent: remember preferences, decisions, and project context across sessions, and recall them on demand.",
-  "author": { "name": "Mem0", "email": "support@mem0.ai", "url": "https://mem0.ai" },
-  "homepage": "https://mem0.ai",
-  "repository": "https://github.com/mem0ai/mem0",
-  "license": "Apache-2.0",
-  "keywords": ["memory", "long-term-memory", "personalization", "mcp"]
-}