Skip to main content
ScriptAI Agentsv1.0

Agent Evaluation Framework

by AaaS · open-source · Last verified 2026-03-01

Evaluates AI agent performance across defined test scenarios with success criteria, step tracking, and automated scoring. Supports custom evaluation rubrics, regression detection, and generates detailed reports comparing agent versions over time.

https://aaas.blog/script/agent-evaluation-framework
C
CBelow Average
Adoption: C+Quality: AFreshness: ACitations: CEngagement: F

Specifications

License
MIT
Pricing
open-source
Capabilities
scenario-testing, success-criteria-evaluation, step-tracking, regression-detection, report-generation
Integrations
@anthropic-ai/sdk, openai, vitest, zod
Use Cases
agent-quality-assurance, regression-testing, capability-assessment, version-comparison
API Available
No
Language
typescript
Dependencies
@anthropic-ai/sdk, openai, vitest, zod, winston
Environment
Node.js 20+
Est. Runtime
5-30 minutes depending on scenario count
Tags
script, automation, evaluation, testing, agents
Added
2026-03-17
Completeness
100%

Index Score

48.3
Adoption
50
Quality
84
Freshness
86
Citations
46
Engagement
0

Explore the full AI ecosystem on Agents as a Service