ThoughtWorks Technology Radar Vol.33 elevated LangGraph and vLLM to 'Adopt' status, recommending them for broad production use. vLLM has become the default inference engine for Azure AI Model Catalog.
88%
Overall ConfidenceBased on 5 weighted dimensions
Confidence Breakdown
Authority
30%80Tier 2
Data Quality
25%80Level 4
Recency
20%6031-90 days
Corroboration
15%1003 sources
Specificity
10%100Level 4
Data Points(3)
LangGraph provides low-level primitives for stateful multi-agent applications
Nov 1, 2025vLLM is now Azure's default inference engine due to high throughput and efficient memory management
Nov 1, 2025Pydantic AI v1.0 released September 4, 2025 marking production maturity
Nov 1, 2025