Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026

PandasAI by Sinaptik AI

A Python library that turns natural-language questions into Python and SQL, runs it against dataframes, databases and data lakes, and returns answers and charts.

AI data analysis agents Open-source conversational data analysis libraryOpen source · MITFree to start

Use it in: API / SDK Works with: Own API key

Price
Free
free tier available
Popularity
#1 in Data
Gid Score 32 / 100 · #148 of 255 ranked AI agents
Trend
Steady
downloads up 3.5% over 30 days · up 6.7% last week
Development
Quiet lately
latest 3.0.0, 13mo ago
Community
24K GitHub stars
8,486 package downloads a week

Usage data: latest readings Nov 19 to Nov 21, 2026, last checked Nov 21, 06:33 UTC. Date of each number

What PandasAI does

PandasAI is an open-source conversational data analysis library from Sinaptik AI, first released in April 2023. You use it through an SDK. Its documentation covers your own API key. It is used from Python. It is free and open source (MIT); you pay only for the models it calls.

Key facts

MakerSinaptik AI
TypeOpen-source conversational data analysis library
First releasedApril 2023
LicenseMIT
InterfacesSDK
Main languagePython
Open issues and PRs24

Pricing

The open-source library is free (MIT, except an enterprise directory under its own licence); cloud and enterprise editions have no public prices.

Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

What's new in PandasAI: October 2025

Full monthly summary

October brought stability improvements and bug fixes to PandasAI 3.0.0, with particular focus on resolving issues in cloud LLM backends and Next.js integration.

  • Fixed Azure OpenAI LLM backend integration
  • Resolved maximum recursion depth error in SmartDataframe
  • Fixed build-time request issues in Next.js environments
  • Improved malicious code scanning

1 release this month · summarised from the official release notes · all months

AgentGid articles about PandasAI

All guides

Get started with PandasAI

PyPIpip install pandasai

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Compare PandasAI with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
191
HexPromoHex Technologies Inc.
262/4 — — — — — Free + $36/mo
225
WrenAICanner
21 — — — 18.4K+26/day 0.18.011d ago Free + $179/mo yearly
249
Helix Foundry NewHelixDB
15 — — — 2,177+9/day — Free + $100/mo
—
— — — — — — Usage-based
—
Julius AIJulius AI
— — — — — — Free + $20/mo
—
— — — — — — Free + $16.58/mo

Head to head: PandasAI vs Hex · PandasAI vs WrenAI · PandasAI vs Helix Foundry · PandasAI vs Databricks Genie · PandasAI vs Julius AI · PandasAI vs Powerdrill Bloom

Tools used with PandasAI

All tools

What 220 public GitHub projects that depend on PandasAI use with it, from their dependency files.

  1. pandas76.4%
  2. Streamlit70.5%
  3. python-dotenv55.5%
  4. NumPy54.1%
  5. OpenAI Python Library48.6%
  6. LangChain46.8%
  7. Matplotlib45.0%
  8. PyYAML33.6%
  9. Requests30.9%
  10. Pillow29.1%

Used far more often here than in AI-built projects overall: what sets PandasAI projects apart.

  1. astor19.5% · 611.3×
  2. dataclasses-json17.3% · 180.1×
  3. Altair15.5% · 138.1×
  4. contourpy17.7% · 123.2×
  5. IPython20.5% · 75.3×
  6. fonttools17.3% · 67.5×
  7. pyparsing22.3% · 63.3×
  8. NLTK16.4% · 53.9×

Ratings from people who use PandasAI

No ratings yet. Used PandasAI? Rate it and say what it is good and bad at.

What changed: recent PandasAI releases

Monthly summary · Full changelog

3.0.0
  • Fix Azure OpenAI LLM backend
  • docs: add AWS Bedrock tutorial to the example
  • Added export const dynamic='force-dynamic';
  • Removed _core property on SmartDataframe that causes maximum recursion depth exceeded
  • Fix making requests during the next.js build process
  • Fix server Dockerfile
2.3.2
  • Fix import submodules in generated code
Earlier releases
2.4.2
  • Fix: docker-compose-npm-error
  • fix: remove plt.show if exists in the generated code
  • fix: make seaborn as an optional dependency
  • fix: check if whitelisted lib is actually exists in the additional deps
  • feat(security): add security config to disable it
  • @Charisn made their first contribution in
2.4.1
  • Update last_code_generated in smart_dataframe's init.py
  • @bence-kecskes made their first contribution in
2.4.0
  • chore[Security]: restrict libs to allow specific functionalities
2.3.1
  • Fixed duplicate export dynamics when building client app
  • chore: minor updates in the README
  • Update library.mdx
  • Fix/#1415 Using torch 2.2.0 in macOS x86_64
  • Add /app to PYTHONPATH
  • Update llms.mdx

PandasAI popularity and usage data

PandasAI was downloaded 8,486 times from PyPI in the week ending Nov 19, 2026, up 6.7% on the week before and up 3.5% over the last 30 days compared with the 30 before. The GitHub repository has 24K stars, 102 of them added in the last 30 days. The latest stable release is 3.0.0, published Oct 7, 2025.

Downloads per dayPyPI, 7-day average 1,212/day
GitHub starsrunning total 24K
Website rankTranco list; a lower rank means more traffic #1,549,460

Download the raw daily series: pandasai.csv

Gid Score breakdown

Adoption21
Community58
Attention—
Momentum52

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 19, 2026Nov 21, 06:24 UTC
GitHub starsNov 21, 2026Nov 21, 06:26 UTC
Website rank (Tranco)Nov 20, 2026Nov 21, 06:33 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

PandasAI FAQ

How much does PandasAI cost?

The open-source library is free (MIT, except an enterprise directory under its own licence); cloud and enterprise editions have no public prices.

Is PandasAI open source?

Yes. PandasAI is open source, released under the MIT license.

How popular is PandasAI?

PandasAI was downloaded 8,486 times from PyPI in the week ending Nov 19, 2026, up 6.7% on the week before and up 3.5% over the last 30 days compared with the 30 before. The GitHub repository has 24K stars, 102 of them added in the last 30 days. The latest stable release is 3.0.0, published Oct 7, 2025.

What is the latest version of PandasAI?

The latest stable release we track is 3.0.0, published on Oct 7, 2025.

What are the alternatives to PandasAI?

The closest alternatives in the same category by Gid Score are Hex, WrenAI, Helix Foundry, Databricks Genie.

For the makers of PandasAI badges, corrections

Add a live badge to your README or site:

AgentGid: #1 in Data Gid Score: 32/100 downloads: 8,486/week ▲4% 30d

[![AgentGid: #1 in Data](https://agentgid.com/badges/pandasai-rank.svg)](https://agentgid.com/agents/pandasai/)
[![Gid Score: 32/100](https://agentgid.com/badges/pandasai-score.svg)](https://agentgid.com/agents/pandasai/)
[![downloads: 8,486/week ▲4% 30d](https://agentgid.com/badges/pandasai-downloads.svg)](https://agentgid.com/agents/pandasai/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

PyPI: pandasai. GitHub: sinaptik-ai/pandas-ai. Site rank: pandas-ai.com on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: github.com, docs.pandas-ai.com.