I built a self-hostable AI data analyst — 4 agents, sandboxed code execution, your choice of LLM

Description and use

<p>Every time I needed to explore a dataset quickly, the same wall appeared: spin up a notebook, deal with encoding errors, write the cleaning boilerplate, decide which chart type actually makes sense, iterate when the data has surprises. The mechanical parts — null handling, imputation, finding correlations, picking a visualization — aren't interesting work. They're just in the way.</p> <p>Tools like ChatGPT's Code Interpreter or Julius AI solve this. But they upload your data to a cloud you don't control, lock you into one LLM, and charge per seat. I wanted something that ran on my own hardw

Problem

<p>Every time I needed to explore a dataset quickly, the same wall appeared: spin up a notebook, deal with encoding errors, write the cleaning boilerplate, decide which chart type actually makes sense, iterate when the data has surprises. The mechanical parts — null handling, imputation, finding correlations, picking a visualization — aren't interesting work. They're just in the way.</p> <p>Tools like ChatGPT's Code Interpreter or Julius AI solve this. But they upload your data to a cloud you don't control, lock you into one LLM, and charge per seat. I wanted something that ran on my own hardw

Outcome

<p>Every time I needed to explore a dataset quickly, the same wall appeared: spin up a notebook, deal with encoding errors, write the cleaning boilerplate, decide which chart type actually makes sense, iterate when the data has surprises. The mechanical parts — null handling, imputation, finding correlations, picking a visualization — aren't interesting work. They're just in the way.</p> <p>Tools like ChatGPT's Code Interpreter or Julius AI solve this. But they upload your data to a cloud you don't control, lock you into one LLM, and charge per seat. I wanted something that ran on my own hardw

Evidence

I built a self-hostable AI data analyst — 4 agents, sandboxed code execution, your choice of LLM

Source