Engineering 20
- Two backends, two stores, one TaskManager: how NeuroLink schedules AI work
- NeuroLink Brownfield Integration: Express & Fastify Adapters
- Voice as Three Stream Topologies: TTS, STT, and Full-Duplex Realtime
- Inside NeuroLink's RAG: The generate() Integration Bridge
- Grading the model: the scorer hierarchy and evaluation pipeline
- Why Every Native Provider Must Wire the Same Tool-Persistence Hook
- Inside ConversationMemoryFactory: How NeuroLink Picks and Wires a Memory Backend
- Twenty-four providers, one BaseProvider: the adapter catalog
- From User Input to Provider API: The Five-Stage Message Flow
- Seventeen file processors, six categories, one priority system
- Four-stage context compaction: what runs when the model window fills up
- What You Actually Inherit When You Extend BaseProvider
- Ten ESLint rules that hold NeuroLink's type system together
- How We Test NeuroLink: 20 Continuous Test Suites and Counting
- Meet Tara: From Slack Thread to Merged PR
- How We Scaled to 13 Providers: The Provider Registry Story
- How We Built Multi-Provider Failover: Never Losing an API Call
- How We Built MCP Integration: Supporting 4 Transport Protocols
- How We Built the RAG Pipeline: 10 Chunking Strategies and Why
- How We Built Streaming Tool Calls: Real-Time AI at Scale