Show HN: Resilient AI Worker Queue with Redis, BullMQ, and Budget Kill Switches

This post presents a production template for running fault-tolerant AI agent queues with automatic model failover across providers (OpenAI, Anthropic, Groq, Ollama), jittered exponential backoff retries, and a Redis-backed token-budget kill switch that halts jobs before exceeding spend limits. It uses BullMQ and Redis for dead-letter queues and concurrency limits, plus structured logging for Datadog, Grafana Loki, or CloudWatch. The community edition is MIT-licensed, with a $39 enterprise license adding dashboards, distributed rate-limiting middleware, and setup guidance.