Kanaries

AI assisted exploratory data analysis, from notebooks to desktop

Intermediate
Screenshot of Kanaries, AI assisted exploratory data analysis, from notebooks to desktop

What is Kanaries?

Kanaries is an AI spreadsheet generator tool. Kanaries bundles PyGWalker, GWalkR, Graphic Walker Desktop and an embeddable charting component into one visual analytics stack, with AI chat for querying data in natural language and shareable chart web apps for team review.

Kanaries is a visual analytics workspace built around one goal: getting from a raw dataset to a readable chart without writing a pile of plotting code. The product is not a single app but a family of tools that share an approach. PyGWalker turns a pandas DataFrame into an interactive exploration surface with one line of code inside a Jupyter notebook. GWalkR does the same job for R data frames in RStudio. Graphic Walker Desktop is a native macOS and Windows editor for offline, higher performance work, and the Graphic Walker component lets developers embed the same drag and drop analytics into React, Vue or Angular applications. The hosted Kanaries workspace ties these pieces together with a chat layer called VizChat. In practice the workflow is drag and drop first. Fields are dropped onto shelves to build charts, and the visual output updates as you explore rather than waiting on a rerun. VizChat takes questions in natural language and returns answers drawn from the loaded data, which suits analysts who want a quick read on a distribution or a relationship before committing to a deeper pass. Finished charts can be shared with teammates as web apps so colleagues explore the same data without installing anything. Runcell.dev, the sibling product, adds an AI code agent inside Jupyter that understands the notebook's code and data, offers inline completions and suggests next analytical steps. Who it fits: data scientists and analysts already living in Python or R notebooks, small teams that want an internal BI surface without a heavyweight platform, and developers who need an embeddable charting component rather than another dashboard vendor. Kanaries sits between notebook plotting libraries like matplotlib and full BI suites like Tableau or Power BI. It borrows the exploratory freedom of the first and some of the sharing convenience of the second, at the cost of the governance and enterprise breadth the big platforms carry.

How do you use Kanaries?

  1. 1Choose the entry point that matches your environment
    Decide whether you work mainly in Python notebooks, in RStudio, on the desktop, or inside a web app you are building. Each path has its own install route.
    Kanaries — Choose the entry point that matches your environment
  2. 2Install PyGWalker and open a DataFrame
    Follow the PyGWalker docs to add the package and call it on a pandas DataFrame. The call renders an interactive chart surface directly in the notebook cell.
    Kanaries — Install PyGWalker and open a DataFrame
  3. 3Build charts by dragging fields onto the canvas
    Drop columns onto the encoding shelves to switch chart types and dimensions. The visualization updates as you move fields, which keeps exploration fast.
  4. 4Ask VizChat a question about the data
    Use the chat panel in the Kanaries workspace to request an insight in plain language and read the generated answer alongside the chart.
  5. 5Share the result as a web app
    Publish the finished charts so teammates can open and filter the same data in a browser without installing anything.
    Kanaries — Share the result as a web app
  6. 6Try the embeddable component in a web project
    Developers can test the Graphic Walker component in the playground, then read the integration examples before wiring it into a React, Vue or Angular app.
    Kanaries — Try the embeddable component in a web project

Pros and cons

Pros

  • One line of code turns pandas or R data frames into an interactive exploration appAI
  • Same visual language across notebook, desktop and embedded web contextsAI
  • VizChat answers questions about loaded data in natural languageAI
  • Charts can be shared as web apps so teammates explore without setupAI
  • Desktop build supports offline analysis on macOS and WindowsAI

Cons

  • Pricing tiers are not spelled out on the homepage, so cost needs checking before committingAI
  • The toolset is split across four products, which makes picking the right entry point confusingAI
  • AI chat output quality depends heavily on how clean and well labeled the source data isAI
  • Documentation and community discussion lean technical, with less hand holding for non codersAI
  • No native mobile apps, so exploration is tied to desktop or browser sessionsAI

How much does Kanaries cost?

Free trial

The homepage invites visitors to start a trial, but it does not state a trial length or which products the trial covers.

Learn more

Integrations

Built for pandas DataFrames in Jupyter, R data frames in RStudio, and React, Vue or Angular front ends via the Graphic Walker component.

Learn more

Features

Drag and drop data exploration with live chart updates, one line DataFrame visualization for pandas and R, VizChat natural language queries over loaded data, shareable chart web apps, an offline desktop editor for macOS and Windows, an embeddable analytics component for React, Vue and Angular, and AI code assistance for Jupyter notebooks through Runcell.dev.

Learn more

Frequently asked questions about Kanaries

  • Does Kanaries offer a free trial?
    The homepage invites visitors to start a trial, but it does not state a trial length or which products the trial covers.
  • How do you use Kanaries?
    The walkthrough on this page covers 6 steps: 1. Choose the entry point that matches your environment 2. Install PyGWalker and open a DataFrame 3. Build charts by dragging fields onto the canvas 4. Ask VizChat a question about the data 5. Share the result as a web app 6. Try the embeddable component in a web project.
  • What platforms does Kanaries support?
    Kanaries is available on Web App, MacOS, Windows and Browser extension.
  • What does Kanaries integrate with?
    Built for pandas DataFrames in Jupyter, R data frames in RStudio, and React, Vue or Angular front ends via the Graphic Walker component.
  • What are the limitations of Kanaries?
    Pricing tiers are not spelled out on the homepage, so cost needs checking before committing. The toolset is split across four products, which makes picking the right entry point confusing. AI chat output quality depends heavily on how clean and well labeled the source data is.

Status

StatusActive
Views0
Outbound clicks0
Added10/21/2026

Platforms

Web AppMacOSWindowsBrowser extension

Pricing

FreemiumSubscription