Cleanlab provides a Python library for data quality and machine learning with messy real world data and labels.
Open source
24 alternativesBambooAI
BambooAI analyzes data with a language model in a persistent Python kernel and supports web and Docker workflows.
About BambooAI
BambooAI is an open-source, LLM-driven data analyst that works in a persistent Python kernel, one cell at a time. Given 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 are re-executed in a fresh kernel against the original data. It runs on your machine with your own model keys, and the code the model writes executes in a container rather than under your account. A web app streams each run, keeps the notebook, and lets you ask follow-up questions against the same kernel state; a hosted version is also offered at bambooai.org.
It offers Quick, Deep and Adaptive modes, follow-up chains, memory packs distilled from saved runs, and a plain-language report version rewritten by a second, cheaper model. Documents such as papers, notes or transcripts (up to four per thread) can be parsed into passages with locators and read alongside the data. Web search with cited sources requires a Gemini key. Ten providers are supported, with each seat configured separately.
Key features
- Persistent Python kernel runs one analysis cell at a time, with per-cell checkpoints
- Cited report numbers re-executed in a fresh kernel before the report is shown
- Quick, Deep and Adaptive modes; Adaptive reviewer checks after every eighth turn
- Follow-up questions continue on the same kernel; runs form step-through chains
- Ten providers with per-seat model choice, including local Ollama and vLLM
- Up to four documents per thread parsed into passages with locators
Best for: Data analysts and data scientists who want step-by-step, inspectable analysis in a notebook-style workflow with their own model keys, including people working with sports science and training data.
Good for
- Open source and runnable locally, using your own model keys or open-weights models via a provider or locally
- Model-written code executes in a container rather than under your account
- Every cell, figure, prompt, token count, time and cost is inspectable, and cited numbers are re-run before reporting
Watch out for
- No model is included; self-hosted use requires your own provider keys and configuration of seats
- Web search with cited published figures requires a Gemini key
- Each analysis thread accepts at most four documents
BambooAI at a glance
- Website
- github.com/pgalko/BambooAI
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
BambooAI alternatives
Tools and sites you could use instead, ranked by how closely they match.
oneDAL is a C++ and DPC++ library for accelerated machine learning routines on tabular data, governed by the UXL Foundation.
Open source
24 alternatives
This project profiles data quality and supports exploratory analysis of Pandas and Spark DataFrames.
Open source
24 alternatives
Lance provides an open lakehouse format for multimodal AI, with vector indexing and data versioning.
Open source
24 alternatives
Desbordante profiles data to find patterns and supports data-cleaning scenarios through console and web application interfaces.
Open source
24 alternatives
Optimus supports agile data preparation workflows across Pandas, Dask, cuDF, Vaex, and PySpark.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
BambooAI FAQ
Do I have to install anything to use it?
A hosted version at bambooai.org is described as the same analyst with nothing to install. Self-hosting runs on your machine with your own model keys and container-based code execution.
Which models can I use?
Ten providers are supported: OpenRouter, OpenAI, Anthropic, Google, Groq, Mistral, xAI, DeepSeek, Ollama and vLLM. Each seat, such as analyst, reviewer or rewriter, has its own model and reasoning effort.
How does it check the numbers in its report?
Before the report is shown, the cells it cites are assembled into a script and executed in a fresh kernel against the original data; the closing card states how many numbers reproduced.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.