awesome-openclaw — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Anil-matcha · MCP Server · ★ 997

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is awesome-openclaw safe to install? View the security audit →

About awesome-openclaw

Awesome OpenClaw A curated list of OpenClaw resources, tools, skills, tutorials, articles, and community projects — the open-source self-hosted AI agent taking the world by storm. OpenClaw (formerly Moltbot, originally Clawdbot) is a free and open-source autonomous AI agent created by Peter Steinberger. It runs locally on your machine, connects to 50+ integrations, and lets you chat with AI through WhatsApp, Telegram, Discord, Signal, iMessage, and more — no subscription required. See also: awesome-hermes-agent — curated resources for Hermes Agent (Nous Research), the most common upgrade path from OpenClaw with a native command. awesome-deepseek-harness — curated resources for DeepSeek Harness (), another everything-is-a-plugin agent with a large community plugin ecosystem. What is OpenClaw? OpenClaw is a self-hosted, open-source AI agent that acts as your personal AI assistant — accessible via WhatsApp, Telegram, Discor

agentic-aiai-agentai-automationautonomous-agentsawesomeawesome-listchatbotclawdbotllm-agentlocal-llm

Quick Facts

Stars997
Forks259
CategoryMCP Server
LicenseMIT
Quality Score68.5981076705124/100
Open Issues2
Last Updated2026-08-25
Created2024-04-10
Platformsmcp
Est. Tokens~28k

Compatible Skills

These tools work well together with awesome-openclaw for enhanced workflows:

awesome-openclaw alternative? Top 6 similar tools

Looking for a awesome-openclaw alternative? If you're comparing awesome-openclaw with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • awesome-openclaw by SamurAIGPT · ⭐ 957

    A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdb

  • lobu by lobu-ai · ⭐ 223

    Open-source control plane and runtime for organisational agents: shared company context & brain

  • awesome-openclaw-agents by mergisi · ⭐ 4.0k

    162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!

  • OpenClawChineseTranslation by 1186258278 · ⭐ 3.8k

    🦞 OpenClaw (Clawdbot/Moltbot) 汉化版 - 开源个人 AI 助手中文版 | Claude/ChatGPT LLM 接入 | WhatsApp/Telegram/Discord 多平台 | 每

  • moltis by moltis-org · ⭐ 2.9k

    A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice

  • ouroboros by razzant · ⭐ 1.4k

    Ouroboros — self-creating AI agent. Born Feb 16, 2026.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Frequently Asked Questions

What is awesome-openclaw?

awesome-openclaw is A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdbot) — open-source self-hosted AI agent for WhatsApp, Telegram, Discord & 50+ integrations.. It is categorized as a MCP Server with 997 GitHub stars.

How do I install or use awesome-openclaw?

You can find installation instructions and usage details in the awesome-openclaw GitHub repository at github.com/Anil-matcha/awesome-openclaw. The project has 997 stars and 259 forks, indicating an active community.

What license does awesome-openclaw use?

awesome-openclaw is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to awesome-openclaw?

The top alternatives to awesome-openclaw on Agent Skills Hub include awesome-openclaw, lobu, awesome-openclaw-agents. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools