AI personal assistants: the tech stack of 37 real products
Assistants that act on your email, calendar, tasks or files for you.
What sets them apart
Picks at least twice as common here as among products overall, in decisions at least 10 of them show.
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 |
|---|---|---|---|
| Frontend Framework | 18 of 22 · 82% | — | |
| LLM API | 19 of 22 · 86% | $10/mo · GPT-6 Luna | |
| Hosting | 9 of 19 · 47% | $17/mo · Pay as you go (Lambda + EC2 t4g.small) | |
| Transactional Email | 15 of 18 · 83% | $20/mo · Pro 50k | |
| Database | 5 of 14 · 36% | $25/mo · Pro | |
| Payments | 11 of 12 · 92% | fees on revenue · $410 on $10,000/mo | |
| Backend Framework | 8 of 11 · 73% | — | |
| Authentication | 5 of 9 · 56% | $0/mo · Hobby | |
| Web Analytics | Google Analytics | 6 of 8 · 75% | $0/mo · Standard |
Monthly bills add up to about $72 at the calculators' default usage, list prices; fees on revenue (Stripe) come on top. Set your own usage →
What they chose, decision by decision
Among the AI personal assistants that show each choice, from makers' products and open-source code alike.
Small samples, fewer than 8 products: Product Analytics (PostHog 6, Mixpanel 1) · Vector Database (pgvector 1, Chroma 1) · Lifecycle Email (Loops 6) · AI SDK & Agent Framework (LangChain 2, LlamaIndex 1) · Database Access & ORMs (Prisma 2, Kysely 1) · LLM Observability & Evals (Braintrust 2, Langfuse 1) · Error Monitoring (Sentry 3)
AI personal assistants we track
32 makers' products and 5 open-source projects. Makers' products first.