BullMQ-compatible API. 10x faster. Zero ops. The simplest way to run LLM pipelines, RAG workflows, and batch inference at scale.
// Same BullMQ API you already know
import { Queue, Worker } from 'flashq';
const queue = new Queue('ai-pipeline');
// Push job with dependencies
const embed = await queue.add('embed', { text });
const generate = await queue.add('generate', { prompt }, {
depends_on: [embed.id]
});
// Wait for result
const result = await queue.finished(generate.id);
Everything you need to run production AI pipelines, without the infrastructure headache.
Chain jobs with depends_on. Perfect for RAG pipelines: embed → search → generate. Wait for results with finished().
Control API costs with built-in rate limiting. Never exceed your OpenAI quota again.
Send embeddings, images, and large context windows without workarounds.
Exponential backoff, configurable attempts, dead letter queue for failed jobs.
Same API you already know. Migrate from BullMQ in minutes, not days. Just change your import and you're done.
From indie hackers to production ML pipelines.
Rate limit OpenAI/Anthropic calls. Retry on 429s. Track costs per job.
Chain embed → search → generate with job dependencies. Get results synchronously.
Orchestrate multi-step agent workflows. Handle tool calls and reasoning loops.
Process millions of predictions. 300K jobs/sec throughput. Progress tracking.
Queue Stable Diffusion jobs. Large payloads for images. Webhook on completion.
Parse PDFs, extract text, generate summaries. Handle long-running jobs.
See how we compare to the alternatives.
| Feature | flashQ | BullMQ + Redis | Inngest | AWS SQS |
|---|---|---|---|---|
| BullMQ-compatible API | ✓ | ✓ | ✗ | ✗ |
| No Redis required | ✓ | ✗ | ✓ | ✓ |
| Job dependencies | ✓ | ✓ | ✓ | ✗ |
| Priority queues | ✓ | ✓ | ✗ | ✗ |
| Max payload | 10 MB | ~5 MB | 4 MB | 256 KB |
| Throughput | 300K/sec | 30K/sec | ~10K/sec | ~3K/sec |
| Self-host option | ✓ | ✓ | ✗ | ✗ |
Open source and free to use. Start building with flashQ today.
Yes! flashQ uses the same API as BullMQ. Just change your import from 'bullmq' to 'flashq' and you're done.
Yes. flashQ is open source and available on GitHub. You can self-host with Docker or download the binary.
flashQ supports both in-memory mode and PostgreSQL for persistence with automatic backups.
Yes. flashQ is battle-tested with 104 unit tests and stress tests handling 300K+ jobs/sec.