collaborative-gym — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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

by SALT-NLP · Agent Tool · ★ 145

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

🔒 Is collaborative-gym safe to install? View the security audit →

About collaborative-gym

Latest News 🔥 [2025/12] 📢 New Release: Real User Trajectories Dataset We’ve released a subset of real user trajectories collected through our platform to support research on human-agent collaboration. Download the dataset here! [2025/02] 🎉 Co-Gym (real) is now publicly available! Visit our website to use collaborative agents for travel planning and tabular analysis. We've also open-sourced our UI components for developers to build upon. [2025/01] Initial release with arXiv preprint (check out our Twitter thread for walkthrough video). We are working on releasing Co-Gym (real) web preview for in-the-wild study, alongside tools for developing collaborative agents locally. What is Collaborative Gym? (Use Collaborative Agents Now!) Collaborative Gym (Co-Gym) is a framework for enabling and evaluating Human-Agent Collaboration. Unlike traditional chatbots, Co-Gym allows both human users and AI agents to not only exchange messages but also take actions in a shared workspace. Additionally, unlike autonomous agents that take

agenthuman-agent-collaborationhuman-agent-interactionlarge-language-modelsllm-agent

Quick Facts

Stars145
Forks22
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score72.0550895991402/100
Open Issues2
Last Updated2026-08-20
Created2024-12-18
Platformspython
Est. Tokens~17k

collaborative-gym alternative? Top 6 similar tools

Looking for a collaborative-gym alternative? If you're comparing collaborative-gym 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.

  • Agent-HTML by Sayhi-bzb · ⭐ 542

    You don't need a chat ui but a canvas with ai.

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

  • LLM-Tool-Survey by quchangle1 · ⭐ 489

    This is the repository for the Tool Learning survey.

  • ToolEmu by ryoungj · ⭐ 217

    [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents wit

  • CoAgents by shizhl · ⭐ 214

    Official code for paper "Learning to Use Tools via Cooperative and Interactive Agents"

  • AutoTools by mangopy · ⭐ 180

    Official Repo for WWW 2025 paper "Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agen

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is collaborative-gym?

collaborative-gym is Framework and toolkits for building and evaluating collaborative agents that can work together with humans.. It is categorized as a Agent Tool with 145 GitHub stars.

What programming language is collaborative-gym written in?

collaborative-gym is primarily written in Python. It covers topics such as agent, human-agent-collaboration, human-agent-interaction.

How do I install or use collaborative-gym?

You can find installation instructions and usage details in the collaborative-gym GitHub repository at github.com/SALT-NLP/collaborative-gym. The project has 145 stars and 22 forks, indicating an active community.

What license does collaborative-gym use?

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

What are the best alternatives to collaborative-gym?

The top alternatives to collaborative-gym on Agent Skills Hub include Agent-HTML, wcgw, LLM-Tool-Survey. 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