Databox tech stack

DuckDB

“DuckDB does the heavy lifting for dataset preparation. It lets us process and structure large API responses efficiently, so users get clean, query-ready datasets without the overhead of a heavier database.” — the maker, Sep 2026 ↗

RabbitMQ

“We use RabbitMQ to queue data fetching jobs. It gives us reliable async processing and makes sure every data sync runs without blocking other operations - critical when handling multiple integrations at scale.” — the maker, Sep 2026 ↗

LangChain

“We evaluated several orchestration frameworks before choosing LangGraph for Artifacts. Generating a document isn't one call and done, it's a multi-step flow: pull the data, structure the layout, apply styling, and hold state across follow-ups like "turn this i…” — the maker, Sep 2026 ↗

Claude

“Routines run without anyone watching. That means the reasoning has to hold up on its own, no follow-up question to catch a mistake, no chance to rephrase and try again. Claude does the actual analysis behind every run: reading the data, working out what change…” — the maker, Sep 2026 ↗

OpenAI API

“We use OpenAI alongside Claude for the structured side of every run: pulling the right metric data, parsing what the routine was asked to do, and shaping the result into something clean and consistent, run after run. When a routine fires at 7am with nobody wat…” — the maker, Sep 2026 ↗

“Every MCP server describes its own tools a little differently: different schemas, different parameter names, different response shapes. We use OpenAI alongside Claude for the structured side of MCP Connectors: parsing what an arbitrary server's tools actually…” — the maker, Sep 2026 ↗

Cursor

“For dramatically shortening our build-test-refine cycle. AI-assisted coding directly in the editor made our MCP integration faster and better.” — the maker, Sep 2026 ↗

Claude Code

“Claude was our AI pair programmer throughout the build. We used it to generate API connection configurations, work through edge cases in our dataset logic, and move faster across the entire development cycle. It also powers the AI-assisted setup experience we…” — the maker, Sep 2026 ↗

“MCP Connectors means implementing an open protocol correctly: parsing tool schemas from any server a user points us to, handling three different auth flows (OAuth, API key, bearer token), and building permission logic that fails safe by default, since this fea…” — the maker, Sep 2026 ↗