AI personal assistants tech stack 2026: what 35 real products use
Assistants that act on your email, calendar, tasks or files for you.
Among the 35 products we track in AI personal assistants, the usual stack is Vercel (hosting, 63%), Next.js (frontend framework, 82%), OpenAI API (LLM API, 84%) and Resend (transactional email, 82%): 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 |
|---|---|---|---|
| Hosting | 17 of 27 · 63% | $40/mo · Pro + Flat Rate CDN 10M | |
| Frontend Framework | 18 of 22 · 82% | — | |
| LLM API | 16 of 19 · 84% | $10/mo · GPT-6 Luna | |
| Transactional Email | 14 of 17 · 82% | $20/mo · Pro 50k | |
| Database | 5 of 12 · 42% | $25/mo · Pro | |
| Payments | 11 of 11 · 100% | fees on revenue · $410 on $10,000/mo | |
| Backend Framework | 7 of 9 · 78% | — | |
| Authentication | 4 of 8 · 50% | $0/mo · Hobby |
Monthly bills add up to about $95 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 personal assistants 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 personal assistants 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: Speech-to-Text & Text-to-Speech (Deepgram 4, ElevenLabs 2) · Web Analytics (Google Analytics 5, Cloudflare Web Analytics 2) · AI SDK & Agent Framework (LangChain 2, LlamaIndex 1) · Product Analytics (PostHog 5, Mixpanel 1) · Vector Database (pgvector 1, Chroma 1) · Lifecycle Email (Loops 5) · LLM Observability & Evals (Braintrust 2, Langfuse 1) · MCP Server for Your Product (MCP SDK 5) · Database Access & ORMs (Prisma 2, SQLAlchemy 1) · Run Models Locally (Ollama 2, Llama 2) · Search APIs for AI (Exa 2, Perplexity API 2) · Tool Integrations for Agents (Composio 4) · AI UI Design (shadcn/ui 3) · Error Monitoring (Sentry 3)
AI personal assistants we track
31 makers' products and 4 open-source projects, makers' products first, each with the tools it uses (the most common here first).
Questions
What tech stack is behind AI personal assistants?
Among the 35 products we track in AI personal assistants, the usual stack is Vercel (hosting, 63%), Next.js (frontend framework, 82%), OpenAI API (LLM API, 84%) and Resend (transactional email, 82%): shares of the products that show each decision. After those, Supabase leads database, Stripe leads payments and FastAPI leads backend framework.
Which tools are more common in AI personal assistants than elsewhere?
Amazon Web Services for hosting (2.7× as often as among products overall).
How much does a typical AI personal assistants stack cost?
About $95 a month in bills at the pricing calculators' default usage and list prices, plus Stripe fees on revenue. The biggest lines: Vercel $40, Supabase $25 and Resend $20.
Which products in AI personal assistants are open source?
4 of the 35 are open-source projects, known from their public code, among them alfred, NagaAgent, Linguflex and aiva.