Metadata-Version: 2.4
Name: bambooai
Version: 2.0.0
Summary: An analyst that works in a notebook: one model, one kernel, one report - with a web app, running on your own machine.
Author: Palo Galko
License: MIT
Project-URL: Homepage, https://github.com/pgalko/BambooAI
Project-URL: Repository, https://github.com/pgalko/BambooAI
Keywords: data analysis,llm,pandas,notebook,agent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: flask>=3.0
Requires-Dist: python-dotenv
Requires-Dist: requests
Requires-Dist: httpx
Requires-Dist: openai>=1.30
Requires-Dist: anthropic
Requires-Dist: google-genai
Requires-Dist: google-generativeai
Requires-Dist: groq
Requires-Dist: mistralai
Requires-Dist: ollama
Requires-Dist: tiktoken
Requires-Dist: termcolor
Requires-Dist: pandas>=2.0
Requires-Dist: numpy
Requires-Dist: pyarrow
Requires-Dist: matplotlib
Requires-Dist: seaborn
Requires-Dist: plotly
Requires-Dist: statsmodels
Requires-Dist: scipy
Requires-Dist: scikit-learn
Requires-Dist: ipython
Requires-Dist: nbformat
Requires-Dist: cryptography
Requires-Dist: newspaper3k
Requires-Dist: lxml_html_clean
Requires-Dist: sweatstack
Requires-Dist: openpyxl
Requires-Dist: pyyaml
Requires-Dist: gunicorn; sys_platform != "win32"
Provides-Extra: analysis
Requires-Dist: geopandas; extra == "analysis"
Requires-Dist: yfinance; extra == "analysis"
Requires-Dist: kaleido; extra == "analysis"
Provides-Extra: dev
Requires-Dist: playwright; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: fitparse; extra == "dev"
Dynamic: license-file

# BambooAI

An LLM-driven data analyst that works in a persistent Python kernel, one cell at a time, and
reproduces its own results before it reports them. Give it a dataset and a question; it writes and
runs code, reads the output, decides the next step, and ends with a report whose cited numbers have
been re-executed in a fresh kernel. It runs on your machine with your own model keys; the code the
model writes runs in a Docker container, not under your account.

```
pip install bambooai
bambooai serve
```

Requirements: Python 3.11 or newer, and Docker running. The first `serve` creates `~/bambooai`,
writes a `.env` there, builds the executor image and opens the browser. Put a model key in the `.env`
(an OpenRouter key covers the default configuration) and start again.

Documentation, configuration and the source: https://github.com/pgalko/BambooAI

Hosted version: https://bambooai.org

BambooAI 1.x was a notebook library; it remains installable as `bambooai<2`.
