BambooAI

Overview of BambooAI

What it is

BambooAI is an LLM-driven data analysis environment built around a persistent Python kernel, an explicit analysis protocol, and a fully inspectable computational record. A primary Analyst model works through a question iteratively, with each turn having one action: run a Python cell, inspect earlier output, search or read supporting material, ask for clarification, or write the report. Executed cells remain in a persistent workspace, allowing later steps and follow-up questions to build directly on earlier computation. The aim is to keep the analytical process visible rather than hiding it behind a final answer. Numerical results reported by the Analyst are tied to the cells that produced them, making it possible to trace a conclusion back through the computation that supports it. At the end of a run, the relevant analysis is assembled and executed again against the original data in a fresh kernel to check reproducibility. Adaptive runs can additionally use a separate Reviewer model to inspect evidence and challenge the method.

Key features

• Iterative analysis: one primary Analyst works through the problem turn by turn in a persistent Python workspace.
• Transactional execution: the kernel keeps a checkpoint after every committed cell; if a cell fails, the previous namespace is restored.
• Evidence-linked results: numerical estimates are recorded when computed and remain associated with the cells that produced them.
• Full visibility: executed code, outputs, figures, intermediate results, working notes, prompts, model usage, timing and cost remain available.
• Reproduction: before completion, the successful computation through the report's supporting cells is rerun against the original data in a fresh kernel.
• Independent review: adaptive mode introduces a separate Reviewer role with its own prompt and model configuration.
• Model-independent orchestration: Analyst, Reviewer, Figures, Rewriter, Reader and other workflow roles can use different models and reasoning settings.

Use cases

BambooAI originated in sports-science and physiological data analysis, where repeated observations, uncertainty, confounding and the provenance of reported results matter. It has integrations with Intervals.icu, Endura and SweatStack. The analysis workflow is general and works with ordinary tabular datasets, supporting documents and external sources. Completed analyses can be saved as routines, which extract the small set of inputs that may change and execute the same recorded method against new data without another LLM analysis.

Getting started

bash pip install bambooai bambooai serve On first use, the app creates the working folder ~/bambooai, writes a .env file, builds the executor image, starts the container, and opens http://127.0.0.1:5001. Add a model key to ~/bambooai/.env and restart.

License and pricing

The project is licensed under the MIT License and is open source.

Based on the project's public README and repository metadata.