Meet Tara: From Slack Thread to Merged PR
Two engineers built a coding agent in their spare time. It doubled PR throughput. Meet Tara — the AI that lives in Slack and ships code from a thread.
Welcome to the NeuroLink Blog
Welcome to the official NeuroLink blog - your source for tutorials, guides, and updates on AI integration.
Two backends, two stores, one TaskManager: how NeuroLink schedules AI work
How NeuroLink's TaskManager survives process restarts: BullMQ vs Node timers for scheduling, Redis vs filesystem for persistence, and a nine-phase autoresearch loop.
NeuroLink Brownfield Integration: Express & Fastify Adapters
How BaseServerAdapter, getFrameworkInstance(), and dynamic-import route groups let you mount NeuroLink MCP, proxy, and agent APIs onto a running Express or Fastify app without ceding server lifecycle control.
Voice as Three Stream Topologies: TTS, STT, and Full-Duplex Realtime
How NeuroLink models voice as TTS, STT, and full-duplex — ChunkedAudioStream backpressure, the realtime state machine, and OpenAI vs. Gemini Live divergence.
Inside NeuroLink's RAG: The generate() Integration Bridge
How NeuroLink's prepareRAGTool wires RAG into generate(): extension-based chunking strategy routing, FNV-1a hashing, a 128-dim InMemoryVectorStore, and a dynamically injected search_knowledge_base tool.
Grading the model: the scorer hierarchy and evaluation pipeline
Grading the model: the scorer hierarchy and evaluation pipeline — companion deep-dive for the NeuroLink blog with architectural detail and code examples.
Why Every Native Provider Must Wire the Same Tool-Persistence Hook
Why Every Native Provider Must Wire the Same Tool-Persistence Hook — companion deep-dive for the NeuroLink blog with architectural detail and code examples.
Inside ConversationMemoryFactory: How NeuroLink Picks and Wires a Memory Backend
Inside ConversationMemoryFactory: How NeuroLink Picks and Wires a Memory Backend — companion deep-dive for the NeuroLink blog with architectural detail and code examples.
Twenty-four providers, one BaseProvider: the adapter catalog
Twenty-four providers, one BaseProvider: the adapter catalog — companion deep-dive for the NeuroLink blog with architectural detail and code examples.