opensquilla — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by TokenRhythm · MCP Server · ★ 7.0k

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

🔒 Is opensquilla safe to install? View the security audit →

About opensquilla

OpenSquilla — Token-Efficient AI Agent Same budget, more capability, better results. A microkernel AI agent for your CLI, Web UI, and chat channels. English · 中文 · 日本語 · Français · Deutsch · Español News 📢 2026-08-22 — The English version of our technical report is now on aiXiv: [aixiv.2608

agentaiai-agentsdeep-learningfoundation-modelsllmmcpmemoryopenclawpython

Quick Facts

Stars7,033
Forks569
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score66.2853788996873/100
Open Issues232
Last Updated2026-09-21
Created2026-05-06
Platformsmcp, python
Est. Tokens~22k

Compatible Skills

These tools work well together with opensquilla for enhanced workflows:

  • opensquilla — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • auto-deep-researcher-24x7 — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • cheetahclaws — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • llm_agents — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • SkillClaw — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)

opensquilla alternative? Top 6 similar tools

Looking for a opensquilla alternative? If you're comparing opensquilla 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.

  • opensquilla by opensquilla · ⭐ 6.9k

    OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

  • AI-Infra-Guard by Tencent · ⭐ 6.4k

    A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca

  • mcp-agent by lastmile-ai · ⭐ 8.5k

    Build effective agents using Model Context Protocol and simple workflow patterns

  • honcho by plastic-labs · ⭐ 7.0k

    Memory library for building stateful agents

  • cursor-talk-to-figma-mcp by grab · ⭐ 7.0k

    TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c

  • EverMemOS by EverMind-AI · ⭐ 3.5k

    A memory OS that makes your OpenClaw agents more personal while saving tokens.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is opensquilla?

opensquilla is OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density. It is categorized as a MCP Server with 7.0k GitHub stars.

What programming language is opensquilla written in?

opensquilla is primarily written in Python. It covers topics such as agent, ai, ai-agents.

How do I install or use opensquilla?

You can find installation instructions and usage details in the opensquilla GitHub repository at github.com/TokenRhythm/opensquilla. The project has 7.0k stars and 569 forks, indicating an active community.

What license does opensquilla use?

opensquilla is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to opensquilla?

The top alternatives to opensquilla on Agent Skills Hub include opensquilla, AI-Infra-Guard, mcp-agent. 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