OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Data Agents

Bambooai

BambooAI is an LLM-driven data analyst that accepts datasets and questions, writes and runs Python in a persistent kernel, examines intermediate results, and produces reports whose cited figures are re-executed in a fresh kernel.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Bambooai — OpenViST project profile in Data Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use BambooAI when you want an interactive, inspectable Python workflow for dataset questions and a report that re-runs its cited figures against the original data.

Who it is for

  • Data analysts who want to ask natural-language questions about tabular datasets.
  • Python users who value visible analysis cells and intermediate outputs.
  • People who need report figures checked by re-execution before presentation.

Documented uses

  • Explore uploaded CSV, Parquet, JSON or XLSX data by asking a question.
  • Run step-by-step Python analysis and inspect the resulting cells, outputs and figures.
  • Continue an analysis with follow-up questions using the existing kernel state.
  • Produce a report with cited numerical results re-executed in a fresh kernel.
Before you choose

Requirements & limits

The README identifies a hosted version and documents local installation. Local setup requires Python 3.11 or newer, Docker, and a model-provider key. The repository is licensed under MIT.

  • The analysis runs as Python cells in a persistent kernel, and the cited report cells are re-executed in a fresh kernel.
  • Docker is the documented default for running model-written code locally.
  • Supported model connections include hosted providers and local Ollama or vLLM models.
  • A Gemini key enables web search; the core dataset-question workflow uses uploaded data.
  • The README lists specific sports-data integrations and document uploads alongside tabular data.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and start BambooAI locally

Set up the local web application and reach its dataset-analysis interface.

Before you start

  • Python 3.11 or newer.
  • Docker Desktop on macOS or Windows, or Docker Engine on Linux, running.
  • A model-provider API key for the model configuration you use.

Steps

  1. Install the package with the command below.

    Documented command
    pip install bambooai

  2. Run bambooai serve; on first use it creates the working folder, builds the executor image, starts the container and opens the local interface.

  3. Add at least one model key to ~/bambooai/.env.

  4. Run bambooai serve again, upload a CSV, Parquet, JSON or XLSX file, and ask a question.

Expected outcome

A locally running BambooAI web app ready to analyse an uploaded dataset.

Guide limitations

  • The first executor-image build takes several minutes, according to the README.
  • Model-provider keys are needed for the configured model seats.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
pgalko/BambooAI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction