<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
        <title>墨梅博客 - Tag: OpenClaw alternative</title>
        <link>https://momei.app</link>
        <description>Momei Blog - AI-driven, natively internationalized developer blog platform.</description>
        <lastBuildDate>Sun, 14 Jun 2026 14:58:42 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>Momei Blog</generator>
        <language>en-US</language>
        <image>
            <title>墨梅博客 - Tag: OpenClaw alternative</title>
            <url>https://momei.app/logo.png</url>
            <link>https://momei.app</link>
        </image>
        <copyright>© 2026 墨梅博客. All rights reserved.</copyright>
        <atom:link href="https://momei.app/feed/tag/open-claw-alternative.xml" rel="self" type="application/rss+xml"/>
        <item>
            <title><![CDATA[Hermes Agent AI Assistant and Momo Blog Updates | Strawberry Weekly Report - Week 24, 2026]]></title>
            <link>https://momei.app/en-US/posts/2026-24-caomei-weekly-hermes-agent-momei-weekly</link>
            <guid isPermaLink="false">https://momei.app/en-US/posts/2026-24-caomei-weekly-hermes-agent-momei-weekly</guid>
            <pubDate>Sun, 14 Jun 2026 14:58:42 GMT</pubDate>
            <description><![CDATA[Strawberry Weekly Report Week 24: Momo Blog released version v1.20.0, introducing features such as friend link RSS aggregation, Umami self-hosted analytics configuration, along with performance optimizations and multiple bug fixes. The author compared Hermes Agent with OpenClaw a...]]></description>
            <content:encoded><![CDATA[<p><img src="https://oss.cmyr.dev/momei-files/posts/67b1a4c440c040bf/image/20260614145742825-h72injh.png" alt="Hermes Agent AI Assistant and Momo Blog Updates | Strawberry Weekly Report - Week 24, 2026" /></p><blockquote>
<p>This article is published and updated on <a href="https://blog.cmyr.ltd">CaoMeiYouRen’s Blog</a> and synchronized across multiple platforms. For any updates, the version on the blog shall prevail. You can also check the latest version via the <code>Original Link</code> at the end of the article.</p>
</blockquote>
<h2 id="preface" tabindex="-1"><a class="header-anchor" href="#preface">Preface</a></h2>
<p>Welcome to CaoMei Weekly! This is a weekly digest curated by CaoMeiYouRen with the help of AI, aiming to provide you with the latest blog updates, GitHub activities, personal updates, and recommendations from other newsletters.</p>
<p>You can subscribe to CaoMei Weekly updates through the following channels:</p>
<ul>
<li><strong>Blog</strong>: <a href="https://blog.cmyr.ltd">CaoMeiYouRen’s Blog</a></li>
<li><strong>MoMei Blog</strong>: <a href="https://momei.app">MoMei Blog</a></li>
<li><strong>RSS</strong>: <a href="https://blog.cmyr.ltd/weekly.xml">CaoMei Weekly</a></li>
<li><strong>Official Account</strong>: <a href="https://oss.cmyr.dev/images/20241025184516839-21n2ctv.png">CaoMeiYouRen’s Backyard</a></li>
<li><strong>Email Subscription</strong>: <a href="https://listmonk.cmyr.dev/subscription/form">CaoMeiYouRen’s Blog Subscription</a></li>
</ul>
<hr>
<h2 id="open-source-updates" tabindex="-1"><a class="header-anchor" href="#open-source-updates">Open-Source Updates</a></h2>
<p>This week, the development of <a href="https://github.com/CaoMeiYouRen/momei">MoMei Blog</a> continues to progress steadily.</p>
<blockquote>
<p>You can try it out on the Demo site: <a href="https://demo.momei.app/">https://demo.momei.app/</a></p>
<ul>
<li>You can log in using the demo admin account with the email <code>admin@example.com</code> and password <code>momei123456</code>.</li>
</ul>
<p>Or register on the official website: <a href="https://momei.app/">https://momei.app/</a></p>
<p>You can also visit the documentation site to learn about the project’s overall plan and future roadmap: <a href="https://docs.momei.app/">https://docs.momei.app/</a></p>
<p>You can now join the waitlist at the bottom of the <a href="https://momei.app/benefits">Benefits</a> page. When the enhanced package is ready, you will be notified via email and other means as soon as possible.</p>
</blockquote>
<p>MoMei Blog has officially released version <a href="https://github.com/CaoMeiYouRen/momei/releases/tag/v1.20.0">1.20.0</a>. Below are some screenshots of the new pages and features.</p>
<p>The backend “Friendship Links” management now includes a “Display RSS Feed” option, allowing you to view the RSS updates of your friends’ links more intuitively.</p>
<p><img src="https://oss.cmyr.dev/images/20260614211750217.png" alt="image-20260614211750042"></p>
<p>Additionally, documentation and configuration examples for integrating self-hosted Umami analytics have been added, along with optimizations to the AI visual prompt generation logic and other improvements.</p>
<p>For more features and pages, you can visit the <a href="https://momei.app/">official website</a> or check out screenshots in previous blog posts.</p>
<p>We welcome all users to try it out and share their feedback and suggestions.</p>
<p>Moving forward, development will continue according to the roadmap and backlog—stay tuned for updates.</p>
<p>Of course, the Momei Blog still has many details to refine, and some features are not yet complete. If you have any suggestions or feedback, feel free to submit them via the project’s <a href="https://github.com/CaoMeiYouRen/momei/issues">GitHub issues</a>.</p>
<p>If you’re also interested in the Momei Blog, you’re welcome to participate in development and testing.</p>
<h2 id="hermes-agent-a-safer-self-learning-ai-assistant-compared-to-openclaw" tabindex="-1"><a class="header-anchor" href="#hermes-agent-a-safer-self-learning-ai-assistant-compared-to-openclaw">Hermes Agent: A Safer, Self-Learning AI Assistant Compared to OpenClaw</a></h2>
<p>Recently, I looked into <a href="https://github.com/NousResearch/hermes-agent">Hermes Agent</a> and found that it’s indeed more user-friendly and secure than OpenClaw.</p>
<p>Here’s the conclusion upfront: After OpenClaw was exposed to multiple critical vulnerabilities in succession, even though I had previously tested it, I no longer trusted it. As a result, I needed an alternative in the same category.</p>
<p>After some research, I chose Hermes Agent as the new AI assistant.</p>
<p>As an open-source project, it’s essential to examine its foundational data. Hermes Agent’s metrics are quite impressive—arguably second only to OpenClaw.</p>
<table>
<thead>
<tr>
<th>Project</th>
<th>Stars</th>
<th>Forks</th>
<th>Issues</th>
<th>PR</th>
<th>License</th>
<th>Language</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>OpenClaw</strong></td>
<td><strong>347,000+</strong></td>
<td>~50,000</td>
<td>469+ open security</td>
<td>Very high frequency</td>
<td>MIT</td>
<td>Node.js/Python</td>
</tr>
<tr>
<td><strong>Hermes Agent</strong></td>
<td><strong>140,000+</strong></td>
<td>~15,000</td>
<td>Active</td>
<td>542 merged (v0.16.0 only)</td>
<td>MIT</td>
<td>Python</td>
</tr>
<tr>
<td><strong>ZeroClaw</strong></td>
<td>29,900+</td>
<td>~3,000</td>
<td>Moderate</td>
<td>Active</td>
<td>MIT</td>
<td>Rust</td>
</tr>
<tr>
<td><strong>Vellum</strong></td>
<td>Rapid growth</td>
<td>—</td>
<td>Active</td>
<td>—</td>
<td>MIT</td>
<td>Rust</td>
</tr>
<tr>
<td><strong>MimiClaw</strong></td>
<td>5,100+</td>
<td>—</td>
<td>Few</td>
<td>—</td>
<td>MIT</td>
<td>C</td>
</tr>
<tr>
<td><strong>NanoClaw</strong></td>
<td>Newest</td>
<td>—</td>
<td>Few</td>
<td>—</td>
<td>MIT</td>
<td>—</td>
</tr>
<tr>
<td><strong>GoClaw</strong></td>
<td>539</td>
<td>—</td>
<td></td>
<td>Few</td>
<td>Active</td>
<td>MIT</td>
</tr>
</tbody>
</table>
<blockquote>
<p>Note: Star/Fork data was collected in June 2026, and the exact numbers may vary due to rapid project changes.</p>
</blockquote>
<p>However, from a comprehensive perspective, OpenClaw has several red flags, such as security vulnerabilities and supply chain risks, which are so severe that they are almost unacceptable.</p>
<table>
<thead>
<tr>
<th>Risk Dimension</th>
<th>OpenClaw</th>
<th>Hermes</th>
<th>Vellum</th>
<th>ZeroClaw</th>
<th>AutoGen</th>
<th>CrewAI</th>
<th>LangGraph</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>Security Vulnerabilities</strong></td>
<td>🔴 Very High</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟡 Medium</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
</tr>
<tr>
<td><strong>Supply Chain Risk</strong></td>
<td>🔴 Very High</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
</tr>
<tr>
<td><strong>Exposure Surface</strong></td>
<td>🔴 Very High</td>
<td>🟡 Medium</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟡 Medium</td>
<td>🟡 Medium</td>
<td>🟡 Medium</td>
</tr>
<tr>
<td><strong>Breaking Changes</strong></td>
<td>🔴 High</td>
<td>🟢 Low</td>
<td>🟢 Low</td>
<td>🟡 Medium</td>
<td>🟡 Medium</td>
<td>🟢 Low</td>
<td>🟡 Medium</td>
</tr>
<tr>
<td><strong>Learning Curve</strong></td>
<td>🟡 Medium</td>
<td>🟡 Medium</td>
<td>🟢 Low</td>
<td>🟡 Medium</td>
<td>🔴 High</td>
<td>🟢 Low</td>
<td>🔴 High</td>
</tr>
<tr>
<td><strong>Vendor Lock-in</strong></td>
<td>🟢 Free</td>
<td>🟢 Free</td>
<td>🟢 Free</td>
<td>🟢 Free</td>
<td>🟡 Azure Bias</td>
<td>🟢 Free</td>
<td>🟡 LangChain Ecosystem</td>
</tr>
<tr>
<td><strong>Data Privacy</strong></td>
<td>⚠️ Model Accessible</td>
<td>🟢 Controlled</td>
<td>🟢 Credential Isolation</td>
<td>🟢 Local</td>
<td>🟢 Controlled</td>
<td>🟢 Controlled</td>
<td>🟢 Controlled</td>
</tr>
<tr>
<td><strong>Community Support</strong></td>
<td>🟢 Largest</td>
<td>🟢 Large</td>
<td>🟡 Growing</td>
<td>🟡 Small</td>
<td>🟢 Large</td>
<td>🟢 Large</td>
<td>🟢 Large</td>
</tr>
</tbody>
</table>
<p>So let’s proceed with another architecture comparison below.</p>
<table>
<thead>
<tr>
<th>Dimension</th>
<th>OpenClaw</th>
<th>Hermes Agent</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>Creator</strong></td>
<td>Peter Steinberger</td>
<td>Nous Research</td>
</tr>
<tr>
<td><strong>Architecture Philosophy</strong></td>
<td>Message-channel driven, ClawHub marketplace</td>
<td>Self-learning loop, built-in evolving skills</td>
</tr>
<tr>
<td><strong>Deployment</strong></td>
<td>Node.js gateway + Docker/local</td>
<td>pip install / Docker / binary</td>
</tr>
<tr>
<td><strong>Message Channels</strong></td>
<td><strong>20+</strong> (WhatsApp, Telegram, Discord, Slack, Signal, iMessage, etc.)</td>
<td>Telegram, Discord, Terminal (fewer but more focused)</td>
</tr>
<tr>
<td><strong>Memory System</strong></td>
<td>Session-level context (requires manual persistence configuration)</td>
<td>Built-in persistent memory + checkpoint/rollback system</td>
</tr>
<tr>
<td><strong>Skill System</strong></td>
<td>ClawHub marketplace (13,729+ skills) ⚠️ Limited community moderation</td>
<td>Built-in self-learning skill creation loop, no public marketplace</td>
</tr>
<tr>
<td><strong>Model Control</strong></td>
<td>Fixed model routing</td>
<td>Fully replaceable, supports local models (Ollama)</td>
</tr>
<tr>
<td><strong>Desktop</strong></td>
<td>```markdown</td>
<td></td>
</tr>
<tr>
<td>App**</td>
<td>❌ No native app (CLI/Web)</td>
<td>✅ v0.15.2+ native desktop app (macOS/Win/Linux)</td>
</tr>
<tr>
<td><strong>Security Model</strong></td>
<td>Operator trust (model has broad tool access)</td>
<td>Smaller attack surface, secure by default</td>
</tr>
<tr>
<td><strong>MCP Support</strong></td>
<td>✅ MCP gateway</td>
<td>✅ Built-in</td>
</tr>
<tr>
<td><strong>Release Cadence</strong></td>
<td>Daily releases, frequent breaking changes</td>
<td>Stable release cycles</td>
</tr>
</tbody>
</table>
<p>In summary, while OpenClaw, as a pioneer, once held a significant advantage, repeated vulnerabilities and disruptive updates have greatly eroded user trust. Meanwhile, Hermes Agent has shown strong momentum in catching up.</p>
<p>After some experimentation, I successfully deployed Hermes Agent, again choosing Feishu as the communication channel. For the AI model, I opted for <code>deepseek-v4-pro</code>, which offers good cost-performance.</p>
<p>Here are a few handy tips:</p>
<ol>
<li>
<p>Hermes Agent supports scheduled tasks. To enhance its autonomous learning capability, you can configure it to automatically scan the past 24 hours of conversations every midnight, extract reusable knowledge, and write it to Memory—saving the effort of manual reminders.</p>
</li>
<li>
<p>Hermes Agent allows separate configuration for vision models. In the <code>auxiliary.vision.model</code> field, I set <code>qwen3.7-plus</code>, addressing <code>deepseek-v4-pro</code>’s lack of multimodal support. Now, even if you send images to Hermes Agent, it can recognize and respond seamlessly.</p>
</li>
</ol>
<p><img src="https://oss.cmyr.dev/images/20260614220340272.png" alt="image-20260614220340115"></p>
<pre><code>
Additionally, when AI-generated results are lengthy, you can request it to generate a file and send it to you.  

Using markdown or docx formats are good options, as they can prevent unsupported markdown formatting characters from appearing in messages.  

![image-20260614220405355](https://oss.cmyr.dev/images/20260614220405504.png)  

More details about Hermes Agent will be covered in future articles—stay tuned.  

## GitHub Release  

### momei  

#### [v1.20.0](https://github.com/CaoMeiYouRen/momei/releases/tag/v1.20.0) - 2026-06-13 21:04:18  
**Summary**:  
- **Code Refactoring**: Refactored AI vision and TTS logic; optimized API caching and cleaned unused endpoints; unified date formatting functions; advanced ESLint type governance (reducing `as any`, merging type definitions); standardized calendar/marketing page routing; reused API schema templates; consolidated settings model and Umami configuration logic; improved readability score calculation.  
- **New Features**: Added support for self-hosted Umami analytics; introduced API query parameter utility functions; implemented AI scoring generation and status prompts; launched a friend link RSS aggregation feature; added a &quot;Show RSS Feed&quot; toggle in backend friend link management; covered Zod schema validation for 3 API endpoints; included user IDs in AI requests and translation functions; supplemented Umami configuration documentation and examples.  
- **Performance Optimizations**: Phase 44 CWV optimizations (Logo preloading + CSS `@import` flattening); reduced PostgreSQL network transfer (removed `author.email` from public listings and unnecessary fields from details).  
- **Bug Fixes**: Limited maximum character count for AI image prompts; optimized date formatting functions; synchronized dependency lock files; updated marketing email templates; fixed ESM imports, rate limits, and empty result caching for friend link RSS feeds; completed missing i18n translations; cleared all lint warnings; added repush functionality and tests for posts; included `showRssFeed` field in `friendLinkSchema`; fixed test lint and type-checking issues.  

## Latest GitHub Starred Repos

- [CaoMeiYouRen starred CopilotKit](https://github.com/CopilotKit/CopilotKit) - 2026-06-13 15:36:40  
  A frontend tech stack project for agents and generative UI, supporting React, Angular, mobile, Slack, and more. It is the creator of the AG-UI protocol, primarily developed in TypeScript, and has 35,064 stars on GitHub.  

- [CaoMeiYouRen starred github-mcp-server](https://github.com/github/github-mcp-server) - 2026-06-11 14:46:45  
  GitHub's official MCP server, mainly developed in Go, with 30,658 stars on GitHub.  

- [CaoMeiYouRen starred Proma](https://github.com/proma-ai/Proma) - 2026-06-10 16:37:15  
  An open-source practice based on the Claude Agent SDK, aiming to provide the smoothest general Agent experience for professional users, currently advancing to the proactive Agent stage. The product natively supports Feishu group chat integration and can flexibly connect to any large model provider. Primarily written in TypeScript, it has 1,265 stars.  

- [CaoMeiYouRen starred deepseek-vision](https://github.com/ErlichLiu/deepseek-vision) - 2026-06-10 16:36:53  
  A proxy service providing visual understanding, web search, and Anthropic/OpenAI-compatible interfaces for the DeepSeek v4 series. Mainly developed in Python, it has 61 stars.  

## Other Blog or Newsletter Recommendations  

### Ruan YiFeng's Network Log  

- [Tech Enthusiast Weekly (Issue 400): The rsync Debate](http://www.ruanyifeng.com/blog/2026/06/weekly-issue-400.html) - 2026-06-12 07:26:08  

### A Cat's Blog

- [Catfish Weekly vol. 098: Journey to Western Sichuan](https://ameow.xyz/archives/weekly-099) - 2026-06-14 18:19:35  

## Summary  

This week's updates and highlights are as shown above. Thank you for reading!  
You can subscribe to Catfish Weekly through the following channels:  

 - **Blog**: [Cao Mei Youren's Blog](https://blog.cmyr.ltd)  
 - **Ink Plum Blog**: [Ink Plum Blog](https://momei.app)  
 - **RSS**: [Catfish Weekly](https://blog.cmyr.ltd/weekly.xml)  
 - **Official Account**: [Cao Mei Youren's Backyard](https://oss.cmyr.dev/images/20241025184516839-21n2ctv.png)  
 - **Email Subscription**: [Cao Mei Youren's Blog Subscription](https://listmonk.cmyr.dev/subscription/form)  

## Past Issues  

- [Ink Plum Blog 1.19.0 Release &amp; Copilot Price Hike Alternatives | Catfish Weekly Issue 23, 2026](https://blog.cmyr.ltd/archives/2026-23-caomei-weekly-momei-blog-1-19-0-release-copilot-price-increase-alternative.html) - 2026-06-08 00:01:57  
- [AI Super Search &amp; Ink Plum Blog Open-Source Updates | Catfish Weekly Issue 22, 2026](https://blog.cmyr.ltd/archives/2026-22-caomei-weekly-super-search-momei-open-source.html) - 2026-05-31 19:59:10  
- [GitHub Copilot Price Surges 37x &amp; Free Search MCP | Catfish Weekly Issue 21, 2026](https://blog.cmyr.ltd/archives/2026-21-caomei-weekly-github-copilot-price-37x-free-search-mcp.html) - 2026-05-18 01:03:14</code></pre>
]]></content:encoded>
            <author>草梅友仁</author>
            <category>Caomei Weekly</category>
            <enclosure length="682605" type="audio/mpeg" url="https://oss.cmyr.dev/momei-files/posts/67b1a4c440c040bf/audio/tts/20260614144036731-h6bcea4.mp3"/>
        </item>
    </channel>
</rss>