Overall LLM Stack Grade
Your LLM infrastructure is needs improvement
How we scored this
Your overall score of 60 (C+) is a weighted average across 19 dimensions. Deprecation Risk is your strongest area at 100 (A), while AI Testing is pulling the score down at 10 (F).
Improving AI Testing from F to a B would add ~2 points to your overall score.
LLM Providers
LLM Call Locations
Models Detected
Files Analyzed
Complexity
3 active signals across 3 categories
2
High Impact
2
Medium Impact
0
Low Impact
Top Priorities
No rate limiting library detected on API calls
highNo observability or cost tracking tools detected
highNo model routing detected — locked to a single model (40-65% savings potential with routing)
medium65,292
Stars
8,222
Forks
94
Open issues
100
Contributors
Languages
71
AI signals in issues
325.7/mo
Fork growth
Overall LLM Stack Grade
Your LLM infrastructure is needs improvement
How we scored this
Your overall score of 60 (C+) is a weighted average across 19 dimensions. Deprecation Risk is your strongest area at 100 (A), while AI Testing is pulling the score down at 10 (F).
Improving AI Testing from F to a B would add ~2 points to your overall score.
LLM Providers
LLM Call Locations
Models Detected
Files Analyzed
Complexity
3 active signals across 3 categories
2
High Impact
2
Medium Impact
0
Low Impact
Top Priorities
No rate limiting library detected on API calls
highNo observability or cost tracking tools detected
highNo model routing detected — locked to a single model (40-65% savings potential with routing)
medium65,292
Stars
8,222
Forks
94
Open issues
100
Contributors
Languages
71
AI signals in issues
325.7/mo
Fork growth
