by open-compass · Codex Skill · ★ 167
[EMNLP 2026] AgentCompass is an extensible open-source evaluation infrastructure for systematically assessing LLM/VLM agent capabilities.
| Stars | 167 |
| Forks | 35 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 41/100 |
| Open Issues | 18 |
| Last Updated | 2026-10-18 |
| Created | 2025-09-04 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~520k |
These tools work well together with AgentCompass for enhanced workflows:
Explore other popular codex skill tools:
AgentCompass is [EMNLP 2026] AgentCompass is an extensible open-source evaluation infrastructure for systematically assessing LLM/VLM agent capabilities.. It is categorized as a Codex Skill with 167 GitHub stars.
AgentCompass is primarily written in Python. It covers topics such as agent, benchmark-framework, claude-code.
You can find installation instructions and usage details in the AgentCompass GitHub repository at github.com/open-compass/AgentCompass. The project has 167 stars and 35 forks, indicating an active community.
AgentCompass is released under the Apache-2.0 license, making it free to use and modify according to the license terms.