AI agents tech stack 2026: what 79 real products use
Agents that carry out multi-step work on their own — research, operations, browsing, back-office tasks.
Among the 79 products we track in AI agents, the usual stack is React (frontend framework, 65%), Vercel (hosting, 57%), OpenAI API (LLM API, 69%) and PostgreSQL (database, 54%): 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.
Monthly bills add up to about $190 at the calculators' default usage, list prices; fees on revenue (Stripe) come on top. Set your own usage →
Where they differ from other products
Tools AI agents 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 agents 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: Image & Video Hosting (sharp 7) · AI App Builders (Lovable 4, Base44 1) · Embeddings (Sentence Transformers 4) · Lifecycle Email (Loops 3, Customer.io 1) · Agent Memory (Mem0 3, Zep 1) · Context & Skills for Coding Agents (Context7 2, Chrome DevTools MCP 1) · Image & Video Generation (Replicate 2, fal 1) · Mobile Framework (Expo 3, React Native 2) · Tool Integrations for Agents (Pipedream 2, Composio 1)
AI agents we track
56 makers' products and 23 open-source projects, makers' products first, each with the tools it uses (the most common here first).
Questions
What tech stack is behind AI agents?
Among the 79 products we track in AI agents, the usual stack is React (frontend framework, 65%), Vercel (hosting, 57%), OpenAI API (LLM API, 69%) and PostgreSQL (database, 54%): shares of the products that show each decision. After those, FastAPI leads backend framework, Resend leads transactional email and LangChain leads AI SDK & agent framework.
Which tools are more common in AI agents than elsewhere?
React Router for frontend framework (2.8× as often as among products overall), Amazon Bedrock for LLM API (2.7× as often as among products overall) and Browserbase for browser automation for agents (2.5× as often as among products overall).
How much does a typical AI agents stack cost?
About $190 a month in bills at the pricing calculators' default usage and list prices, plus Stripe fees on revenue. The biggest lines: Chroma $51, Vercel $40 and Langfuse $29.
Which products in AI agents are open source?
23 of the 79 are open-source projects, known from their public code, among them centaur, iterate, goclaw, mindroom, atom and HugAgentOS.