AI workflow automation tech stack 2026: what 20 real products use
Building automations and workflows that connect apps, with or without AI steps.
Among the 20 products we track in AI workflow automation, the usual stack is OpenAI API (LLM API, 67%), PostgreSQL (database, 62%), React (frontend framework, 92%) and Resend (transactional email, 55%): shares of the products that show each decision.
How they're built
The typical stack
The leading pick where at least 8 of them show the decision and the leader has at least a quarter of it.
| Decision | Most common pick | Share | At default usage |
|---|---|---|---|
| LLM API | 10 of 15 · 67% | $10/mo · GPT-6 Luna | |
| Database | 8 of 13 · 62% | — | |
| Frontend Framework | 12 of 13 · 92% | — | |
| Transactional Email | 6 of 11 · 55% | $20/mo · Pro 50k | |
| AI SDK & Agent Framework | 5 of 9 · 56% | — | |
| Hosting | 7 of 9 · 78% | $40/mo · Pro + Flat Rate CDN 10M | |
| Backend Framework | 4 of 8 · 50% | — | |
| Vector Database | 4 of 8 · 50% | — |
Monthly bills add up to about $70 at the calculators' default usage, list prices. Set your own usage →
Where they differ from other products
Tools AI workflow automation pick at least twice as often as products overall. Each bar is the share of products that show the decision and chose the tool.
What they chose, decision by decision
Among the AI workflow automation that show each choice, from makers' products and open-source code alike. Under each tool, some of the products that chose it.
Small samples, fewer than 8 products: Database Access & ORMs (Prisma 3, SQLAlchemy 3) · Authentication (Clerk 3, Supabase 1) · Background Jobs & Cron (BullMQ 3, Trigger.dev 1) · MCP Server for Your Product (MCP SDK 5, FastMCP 1) · Payments (Stripe 6, Lemon Squeezy 1) · Run Models Locally (Ollama 4, Llama 3) · AI UI Design (shadcn/ui 5) · File Storage (Amazon S3 4, MinIO 3) · Product Analytics (PostHog 5) · Error Monitoring (Sentry 4) · Open Model Hosting & GPUs (Hugging Face 4) · Search APIs for AI (Tavily 2, Exa 1) · Web Scraping for AI (Firecrawl 3, Apify 2) · AI App Builders (Lovable 1, Base44 1) · Document Parsing (PyMuPDF 1, pypdf 1) · Image & Video Generation (HeyGen 2, fal 1) · Image & Video Hosting (sharp 3) · Lifecycle Email (Loops 2, Customer.io 1) · LLM Observability & Evals (Langfuse 3) · Speech-to-Text & Text-to-Speech (ElevenLabs 1, Cartesia 1) · Web Analytics (Cloudflare Web Analytics 2, Vercel Web Analytics 1)
AI workflow automation we track
14 makers' products and 6 open-source projects, makers' products first, each with the tools it uses (the most common here first).
Questions
What tech stack is behind AI workflow automation?
Among the 20 products we track in AI workflow automation, the usual stack is OpenAI API (LLM API, 67%), PostgreSQL (database, 62%), React (frontend framework, 92%) and Resend (transactional email, 55%): shares of the products that show each decision. After those, LangChain leads AI SDK & agent framework, Vercel leads hosting and Express leads backend framework.
Which tools are more common in AI workflow automation than elsewhere?
React for frontend framework (2.1× as often as among products overall).
How much does a typical AI workflow automation stack cost?
About $70 a month in bills at the pricing calculators' default usage and list prices. The biggest lines: Vercel $40, Resend $20 and OpenAI API $10.
Which products in AI workflow automation are open source?
6 of the 20 are open-source projects, known from their public code, among them wavefront, open-agent-builder, AgentPilot, chat-flow, open-gumloop and loonflow.