sogni-gen 1.6.0 → 1.6.1

package/README.md

@@ -7,23 +7,28 @@
 🎨 Generate **images and videos** using [Sogni AI](https://sogni.ai)'s decentralized GPU network.
 
 Works as:
-- an [OpenClaw](https://github.com/OpenClaw/OpenClaw) plugin (recommended)
-- a skill source for Manus AI agent
-- an [MCP server](https://modelcontextprotocol.io/) for **Claude Code** and **Claude Desktop**
+- an [MCP server](https://modelcontextprotocol.io/) for **Claude Code**, **Claude Desktop**, and any MCP-compatible agent
+- an [OpenClaw](https://github.com/OpenClaw/OpenClaw) plugin
+- a skill source for [Hermes Agent](https://hermes-agent.nousresearch.com/), [Manus AI](https://manus.im), and other agent frameworks
+- a standalone Node.js CLI
 
-## Quick Start (OpenClaw + Manus)
+## Quick Start
 
 1. Create Sogni credentials (one-time): see [Setup](#setup).
-2. For OpenClaw, install the plugin:
+2. Install for your platform:
 
 ```bash
+# MCP (Claude Code — one command)
+claude mcp add sogni -- npx -y -p sogni-gen sogni-gen-mcp
+
+# OpenClaw
 openclaw plugins install sogni-gen
-```
 
-3. For Manus AI agent, point it to this repository:
+# Hermes Agent / Manus / other frameworks — point to this repo:
+# https://github.com/Sogni-AI/openclaw-sogni-gen
 
-```
-https://github.com/Sogni-AI/openclaw-sogni-gen
+# Standalone CLI
+npm install -g sogni-gen
 ```
 
 Then ask your agent:
@@ -37,9 +42,9 @@ Then ask your agent:
 - "Generate 3 variations of a sports car in red, blue, and green"
 - "Refine the last image at higher quality"
 
-## OpenClaw Installation (Recommended)
+## Installation
 
-### Plugin Install
+### OpenClaw Plugin
 
 ```bash
 openclaw plugins install sogni-gen
@@ -47,9 +52,9 @@ openclaw plugins install sogni-gen
 
 The installed plugin loads its behavior from [`SKILL.md`](./SKILL.md) via [`openclaw.plugin.json`](./openclaw.plugin.json).
 
-### Optional Install Helper
+### Hermes Agent / Manus / Other Frameworks
 
-[`llm.txt`](https://raw.githubusercontent.com/Sogni-AI/openclaw-sogni-gen/main/llm.txt) is now only a lightweight install/setup helper. It is not the primary behavior source for the installed OpenClaw plugin.
+Point the agent to this repository's [`SKILL.md`](./SKILL.md) for behavior guidance and [`llm.txt`](https://raw.githubusercontent.com/Sogni-AI/openclaw-sogni-gen/main/llm.txt) for install/setup help. The agent can then invoke `sogni-gen` via the CLI or MCP server.
 
 ### Manual Installation
 

package/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: sogni-gen
-version: "1.6.0"
+version: "1.6.1"
 description: Creative AI studio — generate images, videos, and music using Sogni AI's decentralized network. Supports personas (named people with saved reference photos and voice clips), persistent memories (user preferences across sessions), custom personality, style transfer, angle synthesis, and multi-step creative workflows. Ask the agent to "draw", "generate", "create an image", "make a video/animate", "apply a style", or "generate me as a superhero".
 homepage: https://sogni.ai
 metadata:
@@ -41,6 +41,10 @@ metadata:
 
 Generate **images and videos** using Sogni AI's decentralized GPU network.
 
+## MCP vs CLI Routing
+
+If sogni MCP tools are available in your session (e.g., `generate_image`, `manage_personas`), **prefer MCP tools over direct CLI invocation**. MCP tools handle input validation, credential checking, file downloads, and result formatting automatically. Only fall back to the CLI (`node sogni-gen.mjs ...`) if MCP tools are not registered in your environment.
+
 ## Setup
 
 1. **Get Sogni credentials** at https://app.sogni.ai/

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sogni-gen",
-  "version": "1.6.0",
+  "version": "1.6.1",
   "description": "Sogni AI image & video generation — OpenClaw plugin and MCP server for Claude Code / Claude Desktop",
   "type": "module",
   "main": "sogni-gen.mjs",

package/version.mjs

@@ -1 +1 @@
-export const PACKAGE_VERSION = '1.6.0';
+export const PACKAGE_VERSION = '1.6.1';