How Makers Build
Check my stackPlan my stack
Menu
AI assistants & chat

AI search & research tools: the tech stack of 33 real products

Answer engines, research assistants and deep-research tools that cite sources.

What sets them apart

Picks at least twice as common here as among products overall, in decisions at least 10 of them show.

FastAPIBackend Framework2.3×as often as overall12 of the AI search & research tools that show backend framework (80%)

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.

DecisionMost common pickShareAt default usage
LLM APIOpenAI API23 of 27 · 85%$10/mo · GPT-6 Luna
Frontend FrameworkNext.js16 of 19 · 84%—
AI SDK & Agent FrameworkLangChain10 of 18 · 56%—
Backend FrameworkFastAPI12 of 15 · 80%—
DatabasePostgreSQL9 of 14 · 64%—
HostingAmazon Web Services4 of 13 · 31%$17/mo · Pay as you go (Lambda + EC2 t4g.small)
Transactional EmailResend7 of 12 · 58%$20/mo · Pro 50k
Vector Databasepgvector3 of 9 · 33%—

Monthly bills add up to about $47 at the calculators' default usage, list prices. Set your own usage →

What they chose, decision by decision

Among the AI search & research tools that show each choice, from makers' products and open-source code alike.

LLM API27 products
OpenAI API23 · 85%Gemini API11 · 41%Claude8 · 30%Groq3 · 11%
Frontend Framework19 products
Next.js16 · 84%React11 · 58%Vue.js1 · 5%SolidJS1 · 5%
AI SDK & Agent Framework18 products
LangChain10 · 56%AI SDK5 · 28%LlamaIndex4 · 22%LangGraph4 · 22%
Backend Framework15 products
FastAPI12 · 80%Hono2 · 13%Express2 · 13%Flask2 · 13%
Database14 products
PostgreSQL9 · 64%Supabase4 · 29%Neo4j2 · 14%Neon1 · 7%
Hosting13 products
Amazon Web Services4 · 31%Fly.io3 · 23%GitHub Pages3 · 23%Cloudflare2 · 15%
Transactional Email12 products
Resend7 · 58%SendGrid3 · 25%Postmark1 · 8%Amazon SES1 · 8%
Vector Database9 products
pgvector3 · 33%Qdrant2 · 22%Chroma1 · 11%Weaviate1 · 11%

Small samples, fewer than 8 products: Database Access & ORMs (SQLAlchemy 4, Prisma 2) · Payments (Stripe 6, Polar 1) · LLM Observability & Evals (Langfuse 2, Arize Phoenix 2) · Web Analytics (Plausible Analytics 2, Vercel Web Analytics 2) · Background Jobs & Cron (Celery 2, Trigger.dev 1) · File Storage (Amazon S3 3, Vercel Blob 1) · Product Analytics (PostHog 4) · Authentication (Better Auth 2, Clerk 1) · Error Monitoring (Sentry 3) · Image & Video Hosting (sharp 3)

AI search & research tools we track

23 makers' products and 10 open-source projects. Makers' products first.

CortexLet your AI search all your workspace apps, at once+1
MiniculeUse AI to visualize biomedical knowledge
RemyAsk any question and get answers from the world’s videos.
WebhoundResearch agents with a depth dial
ContriveSearch and act across all your work apps
Cure AIYour companion for evidence-based research.
DecodedAI assistants you can email for deep research and more
NormainTrusted insights from complex documents
OnyxThe open source AI teammate you've dreamed of
SiderDeep Research Agent & AI Research Browser Extension
CompetelyInstantly find, analyze, and track your competitors with AI
sciraScira (Formerly MiniPerplx) is a minimalistic AI-powered search engine that helps you find information on the internet and cites it too. Powered by Vercel AI SDK!+16
SurfSenseAir gapped, privacy focused open source NotebookLM alternative. Join our Discord: https://discord.gg/ejRNvftDp9+9
pipeshub-aiPipesHub is an open-source platform for securely connecting enterprise knowledge to AI. Give AI agents trusted context and your team permission-aware search with verified citations across your busines+14
openscienceThe open-source AI workbench for scientific research+13
xyneAI-first Search & Answer Engine for work. Open-source alternative to Glean.+9
khojYour AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI +8
sec-insightsA real world full-stack application using LlamaIndex+5
open-notebookAn Open Source implementation of Notebook LM with more flexibility and features
MiroThinkerMiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
zotero-mcpZotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.
decipher-research-agentTurn topics, links, and files into AI-generated research notebooks — summarize, explore, and ask anything.+3
DeepResearchAgentDeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordi+3
farfalle🔍 AI search engine - self-host with local or cloud LLMs
deep-research-web-uiAI deep-research agent that turns any question into a cited report: plans searches, reads real sources, verifies evidence. Self-hosted, multi-provider, Docker-ready.
AutoRAGAutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.
academic-commercialization-agentTurn papers and research topics into source-linked commercialization assessment drafts. Python, FastAPI and CrewAI; auditable scoring, checkpoint recovery and durable request receipts.
MiroFlow🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI