agentao — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 jin-bo · MCP Server · ★ 305

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

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

About agentao

Agentao (Agent + Tao) "Order in Chaos, Path in Intelligence." Agentao is a Governed Agent Runtime — a local-first, private-first, embeddable agent harness for Python hosts. Permissions, protocols, memory, plugins, and multi-session control are all first-class. 中文版本 README.zh.md 📚 Documentation — read this first The full handbook lives in (VitePress, bilingual). Production site: agentao.cn. agentao.cn/zh/cli/ · [agentao.cn/z

acpagent-frameworkai-agentclillmlocal-firstmcpmodel-context-protocolopenai-compatiblepython

Quick Facts

Stars305
Forks11
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score69.8106254922796/100
Open Issues3
Last Updated2026-09-20
Created2026-02-10
Platformscli, mcp, python
Est. Tokens~15k

agentao alternative? Top 6 similar tools

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

  • fim-one by fim-ai · ⭐ 1.5k

    Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hos

  • LightAgent by wanxingai · ⭐ 1.2k

    LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing,

  • python-utcp by universal-tool-calling-protocol · ⭐ 650

    Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, wi

  • roam-code by Cranot · ⭐ 518

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

  • mcpproxy-go by smart-mcp-proxy · ⭐ 377

    Supercharge AI Agents, Safely

  • omega-memory by omega-memory · ⭐ 218

    Persistent memory for AI coding agents

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is agentao?

agentao is Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.. It is categorized as a MCP Server with 305 GitHub stars.

What programming language is agentao written in?

agentao is primarily written in Python. It covers topics such as acp, agent-framework, ai-agent.

How do I install or use agentao?

You can find installation instructions and usage details in the agentao GitHub repository at github.com/jin-bo/agentao. The project has 305 stars and 11 forks, indicating an active community.

What license does agentao use?

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

What are the best alternatives to agentao?

The top alternatives to agentao on Agent Skills Hub include fim-one, LightAgent, python-utcp. 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