agent-evaluation-direct
OfficialBenchmark and evaluate agents with automated runs
AuthorVibeTechnologies
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Automates the benchmarking and evaluation of multiple AI agents by running predefined tasks through a unified runner and collecting outputs for comparison.
Core Features & Use Cases
- Run single-agent or multi-agent evaluations using python scripts/run_agent.py and aggregate results with agents/benchmark.py.
- Generate structured outputs suitable for scoring and reporting, enabling quick comparisons across frameworks.
- Use Case: Compare AutoGen, CrewAI, and OpenHands on a standard task and produce a concise evaluation report.
Quick Start
Run the evaluation on a sample task using the all option to execute every agent.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agent-evaluation-direct Download link: https://github.com/VibeTechnologies/VibeTeam/archive/main.zip#agent-evaluation-direct Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.