agent-studio — 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 ltzheng · Agent Tool · ★ 232

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

🔒 Is agent-studio safe to install? View the security audit →

About agent-studio

AgentStudio -- AgentStudio is a trinity of environments, tools, and benchmarks for general virtual agents to interact with any computer software. AgentStudio targets the desiderata for robust, general, and open-ended virtual agents by providing: A lightweight, interactive environment with highly generic observation and action spaces, e.g., video observations and GUI/API actions Tools for creating online benchmark tasks, annotating GUI elements, and

ai-agentsbenchmarkenvironmentlanguage-model

Quick Facts

Stars232
Forks31
LanguagePython
CategoryAgent Tool
LicenseAGPL-3.0
Quality Score69.8500584705228/100
Open Issues2
Last Updated2025-06-16
Created2024-01-03
Platformspython
Est. Tokens~1184k

Compatible Skills

These tools work well together with agent-studio for enhanced workflows:

  • AEnvironment — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • ToolEmu — semantic(0.27)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • ToRA — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • ollama-benchmark — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)

agent-studio alternative? Top 6 similar tools

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

  • gateway by adaline · ⭐ 605

    The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for ca

  • AEnvironment by inclusionAI · ⭐ 313

    Standardized environment infrastructure for Agentic AI development.

  • clientai by benavlabs · ⭐ 70

    A unified client for AI providers with built-in agent support.

  • universal-intelligence by blueraai · ⭐ 55

    ◉ Universal Intelligence: AI made simple.

  • claude-codex-settings by fcakyon · ⭐ 1.2k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

  • ToRA by microsoft · ⭐ 1.1k

    ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is agent-studio?

agent-studio is [ICLR 2025] A trinity of environments, tools, and benchmarks for general virtual agents. It is categorized as a Agent Tool with 232 GitHub stars.

What programming language is agent-studio written in?

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

How do I install or use agent-studio?

You can find installation instructions and usage details in the agent-studio GitHub repository at github.com/ltzheng/agent-studio. The project has 232 stars and 31 forks, indicating an active community.

What license does agent-studio use?

agent-studio is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to agent-studio?

The top alternatives to agent-studio on Agent Skills Hub include gateway, AEnvironment, clientai. 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 Agent Tool tools