Open-source CLI and library for testing and evaluating LLM prompts. Run automated evals, red-team your models for safety, and catch regressions before they hit production.
Best For
Teams & solo builders
Key Pros & Cons
Strengths
- 8.9% fork-to-star ratio β strong developer contribution signal
Watch Out For
- Low community score (2/100) β smaller support network
Market Momentum
49
+9
24h
+25
7d
+20
30d
14-day heat score history
Creator Buzz3
Search Interest90
Community Activity2
Abandonment & Maintenance Risk
Low Risk
Trend phaseRising
30-day score change+20 pts
Listed on HookFlow2mo old
Discontinued flagβ No
Commit cadenceVery Active
Last commitToday
Risk Factors
- No major abandonment signals detected
- Active growth β strong maintenance signal
- GitHub repo actively maintained β last commit Today
GitHub Repository Health
A
Very Active
Stars
22,402
Forks
1,999
Open Issues
339
Watchers
59
Last commitToday
7-day star growth+236 stars
Fork / Star ratio8.9%
Snapshot dateJun 20, 2026
Data Lock-In Index
100
/ 100 (lower = more open)
β Webhooks Outβ Bulk Exportβ Open Formats
vs. Category Peers (AI Observability)
Tool
A.R.C.
Heat
7d Ξ
Lock-In
Promptfoo (this)
Prompt testing & evals
β
49
+25
100
Langfuseβ² Rising
Open-source LLM observability
β
51
+27
100
LangSmithβ² Rising
LLM call tracing & evals
β
44
+25
100
Helicone
Snapshot Disclaimer: All scores, rankings, and metrics in this report reflect data as of June 20, 2026. Heat scores, community activity, and market momentum are recalculated daily β figures shown here represent a point-in-time snapshot and may differ from current values on HookFlow.ai.
HookFlow.ai Infrastructure Report β June 20, 2026hookflow.ai