#3232nd of 33 in Agent frameworks and SDKs
pandas-ai
Python library for asking natural-language questions about DataFrames
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 23.9k
- License
- custom license
- Last commit
- Oct 2025
- Last release
- Oct 2025
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
PandasAI adds a chat method to DataFrames. It sends questions to an LLM through LiteLLM, runs the generated code, and returns answers or charts, including across multiple DataFrames. An optional pandasai-docker package runs the generated code in a Docker sandbox. The repo is MIT except the pandasai/ee directory, which has a separate license.
Who it is for: Python data analysts and developers querying DataFrames with an LLM
Strengths
- Two-line usage: read a CSV, then call df.chat() with a question
- Handles questions across several DataFrames and generates charts
- Optional Docker sandbox isolates execution of LLM-generated code
- LLM backend is swappable via the pandasai-litellm package
Weaknesses
- Without the Docker sandbox, generated code runs in your own Python process
- Python 3.8 to 3.11 only, per the README
- pandasai/ee directory is under a separate license; managed and enterprise tiers are paid
- Needs an LLM API key or provider; local model setup is not covered in the README
What it needs
- no GPU
- Compose
- Needs pandasai-litellm, LLM provider API key (e.g. OpenAI), Docker (optional, for sandbox via pandasai-docker)
- Models: LiteLLM-supported providers, OpenAI gpt-4.1-mini (example)
Also in Agent frameworks and SDKs
See all 33| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 92 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 87 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 84 out of 100 |