Orkas — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 Orkas-AI · MCP Server · ★ 2.1k

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

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

About Orkas

Orkas Open-source, local-first desktop app to build and command a team of AI agents — in one chat, with your own LLM keys. Fully offline-capable. macOS · Windows · Linux. English · 简体中文 A commander LLM assembles a team of sub-agents and dispatches them in parallel or in series. Agents self-evolve through reflection. Your conversations, files, and API keys never leave your machine. What is Orkas? What it is — a desktop GUI app where you build a team of specialized AI agents and command them through a single chat. Not a code framework, not a hosted SaaS. Local-first — conversations, files, API keys, knowledge bases, and custom agents all stay on your disk. Model calls go straight from your machine to the provider — never through Orkas servers. Multi-agent (lead + sub-agents) — one commander LLM dispatches sub-agents in parallel or in series; each agent has its own

agent-collaborationagent-orchestrationagent-teamagentic-aiai-agentsai-assistantai-teamai-workflowautonomous-agentsbyo-llm

Quick Facts

Stars2,107
Forks83
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score61.1124786502784/100
Open Issues12
Last Updated2026-09-23
Created2026-04-29
Platformsclaude-code, cli, codex, mcp, node
Est. Tokens~15k

Orkas alternative? Top 6 similar tools

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

  • tutti by tutti-os · ⭐ 3.7k

    Where people and agents build in tune.

  • opencrew by AlexAnys · ⭐ 493

    Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack,让 AI 团队各司其职、自主稳定迭代。

  • CORAL by Human-Agent-Society · ⭐ 961

    Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with gradin

  • deepchat by ThinkInAIXYZ · ⭐ 6.3k

    🐬DeepChat - A smart assistant that connects powerful AI to your personal world

  • ag2 by ag2ai · ⭐ 5.0k

    AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

  • sre by SmythOS · ⭐ 1.3k

    The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular,

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Orkas?

Orkas is Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs your installed coding CLIs — Claude Code, Codex, OpenCode, OpenClaw, Hermes — as local sess. It is categorized as a MCP Server with 2.1k GitHub stars.

What programming language is Orkas written in?

Orkas is primarily written in TypeScript. It covers topics such as agent-collaboration, agent-orchestration, agent-team.

How do I install or use Orkas?

You can find installation instructions and usage details in the Orkas GitHub repository at github.com/Orkas-AI/Orkas. The project has 2.1k stars and 83 forks, indicating an active community.

What license does Orkas use?

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

What are the best alternatives to Orkas?

The top alternatives to Orkas on Agent Skills Hub include tutti, opencrew, CORAL. 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