by SALT-NLP · Agent Tool · ★ 172
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: sudo usage. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 172 |
| Forks | 23 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 72/100 |
| Open Issues | 5 |
| Last Updated | 2026-08-20 |
| Created | 2024-12-18 |
| Platforms | python |
| Est. Tokens | ~17k |
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.
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.
You don't need a chat ui but a canvas with ai.
ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.
Shell and coding agent on mcp clients
This is the repository for the Tool Learning survey.
[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents wit
Official code for paper "Learning to Use Tools via Cooperative and Interactive Agents"
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: