The AI tooling ecosystem has matured fast. Here is what members of AI Underground are actually using across our Vancouver and Dubai communities right now.

For Building AI Applications

• Vapi.ai – Fastest path to a working voice agent, handles STT, LLM, and TTS
• Instructor – Structured outputs from LLMs every time
• LangChain and LlamaIndex – Still useful for complex pipelines
• DSPy – Best for serious prompt optimisation at scale

For Vector Storage

• pgvector – If you are already on Postgres, start here
• Qdrant – Best performance for high-scale vector search
• Weaviate – Good hybrid search out of the box

For Observability

• Langfuse – Open source LLM observability with cost tracking
• RAGAS – Automated evaluation for RAG pipelines
• Braintrust – Good for teams running continuous evals in CI

Come to AI Underground and tell us what you are shipping. Vancouver every Thursday, Dubai every Friday. Both free.