ExaktAI Workspace

Download — Beta opens Sep 9

The Workspace is a computational environment where mathematical computing systems work together. Mathematics is the language: write in the SymPy, Maple, Mathematica or MATLAB dialect, and compute with the software you choose. A document written in Maple's notation can compute on SymPy; a Mathematica one, on Maple; a MATLAB one, on NumPy and SymPy. AI mathematics is here to stay, and the Workspace is where you can follow, reproduce, modify, and extend it, or simply do the mathematics yourself.

The Workspace

In the Workspace document, text, executable mathematical input, and results are interleaved. Results are typeset and numbered so they can be referenced in later computations. You can move freely through the document, revise any earlier computation, and run it again. Plots are interactive by default: you can zoom and pan them, or read a value off the curve. You can split the screen, keeping the upper pane in view while you write in the lower one. This is the full computer-algebra interface, familiar to users of Maple worksheets, Mathematica notebooks, and MATLAB Live Scripts. The interface comes in three themes, ExaktAI, Light, and Dark, and includes an AI assistant that opens in a separate window. The assistant can use your paid AI subscriptions or limited no-charge access to Gemini and Groq.

The ExaktAI Workspace includes SymPy, NumPy, SciPy and Matplotlib^*, and drives your own Maple, Mathematica or MATLAB, or the Wolfram Engine, which you can install free for non-commercial, personal use.

Dialect you write	SymPy	Maple	Mathematica	MATLAB
	Engine that computes
SymPy	runs as written	translated	translated	translated
Maple	translated	runs as written	translated	translated
Mathematica	translated	translated	runs as written	translated
MATLAB	translated	translated	translated	runs as written

Every document has its dialect and engine set, shown in the chip at its corner. Clicking the chip changes the dialect, the engine, or both, and changing the dialect rewrites the inputs of the document into the new one. Translation between dialects has limits: not every command exists in all four systems. It is a growing capability.

A computer algebra system (CAS) whose dialect is SymPy

A computer algebra environment for the Python scientific stack: SymPy, NumPy, SciPy and Matplotlib.

The commands are SymPy's own, read as mathematics: no imports and no declaring symbols, a free name declares itself, x^2 is a power, 3/2 stays exact, == makes an equation rather than a true/false verdict. Edit a line above and run it again, carry a result forward by its equation label, read output as typeset mathematics, or the same mathematics inline in a text region, and organise the whole with sections, subsections and hyperlinks. In Presentation mode, Export as LaTeX writes the document out as a paper.

The SymPy 101 tutorial that ships with the ExaktAI Workspace, twice: on the left its thirteen sections collapsed, from exact arithmetic to a differential equation; on the right section twelve open, deriving a projectile's range with solve and trigsimp and plotting the trajectory, both chips reading sympy to sympy with the CAS badge lit — The SymPy 101 that ships with the Workspace on the left, one of its sections run on the right. The chip **(sympy → sympy)** indicates the dialect and engine. Results are numbered and reusable by their number. The **CAS** badge is lit: `x^2` is a power, `3/2` exact, `==` an equation.

NumPy, SciPy and Matplotlib are bundled beside SymPy and run as themselves: their numbers are machine floats, and a region that computes with them stays a program. The symbolic mathematics is SymPy's; NumPy arrays, SciPy computations and Matplotlib figures keep Python's own semantics.

The Workspace includes an AI assistant beside the document, its own help pages, CAS 101 tutorials for each of the dialects, and a help page for each command it covers in the SymPy, Maple and Mathematica dialects. F1 on a command you typed opens its help page; hovering a typeset function in the output shows how it is written in the dialect, and links to its page. And the Digital Library of Mathematical Functions opens in a window of its own, where an identity on one of its pages is taken into the document, written directly in the document's dialect, ready to use.

Open what you already have

Maple, Mathematica, MATLAB, Jupyter and Python files, decoded natively.

A notebook of your own opens as it was written: its SymPy, NumPy and SciPy code keeps Python's own semantics, and the stack that runs it is included in the Workspace. What is new is around it, the document now being one of your collection, with the engines, the labels and the assistant beside it.

Or the same notebook is imported as a CAS document: the imports and symbol declarations the CAS reading does not need are omitted, the notation becomes the dialect's, and the author's comments become the document's text. Regions that are programs, computing with NumPy or SciPy on machine numbers, stay programs.

The same Jupyter notebook for SymPy open twice in the ExaktAI Workspace: on the left as written, with symbols declared by hand and A**2 in Python notation; on the right imported as a CAS document, where the declarations are gone, the matrices are typeset, and A squared and A times b are shown in CAS notation — One notebook, twice. Opened as written on the left, *imported as a CAS document* on the right, where the declarations the CAS reading does not need are omitted and the notation is read as mathematics: the same computation in its CAS-document form.

The chip at the top right says which reading a document is in: the CAS badge lit for SymPy read as mathematics, dimmed for literal Python. Clicking it rewrites the document's inputs into the other reading, in either direction.

A Maple worksheet (.mw), a Mathematica notebook (.nb), a MATLAB script (.m) or Live Script (.mlx) are read directly, with no Maple, no Mathematica and no MATLAB required on the computer. Where the document's constructs all translate, the bundled SymPy, NumPy and SciPy run the computations written in your imported dialect. For a Mathematica document, you can install the Wolfram Engine, free for non-commercial, personal use, and run it on Wolfram's own computational engine. And if you have Maple, Mathematica or MATLAB, a right click on any line offers to run that line using a different CAS engine.

Two ExaktAI Workspace documents side by side: on the left a MATLAB-notation document whose chip reads matlab to sympy, an ode45 integration and its plot computed by the bundled SymPy, NumPy and SciPy; on the right a Mathematica-notation document, mathematica to sympy, with the right-click menu open on an Integrate line offering Execute in SymPy, Execute in Maple with a check mark and the hint option-as-written, Execute in Mathematica and Execute in MATLAB, and results badged Maple or Mathematica, the engine that answered that line. — A MATLAB document and a Mathematica document, both computing on the bundled SymPy, NumPy and SciPy, on a computer with neither installed: the chips read **matlab → sympy** and **mathematica → sympy**. The menu on the right is the other half of that freedom: one line sent to another engine, its answer badged with whichever engine computed it.

A MATLAB Live Script opens with its headings, formatted text, lists and figures in place, its code runnable. If you don't have MATLAB installed, the engine is set to SymPy, the arrays and the differential equations are handled by NumPy and SciPy, and SymPy answers the symbolic commands in the Symbolic Math Toolbox's own spellings: syms, int, solve and taylor among them.

If you already own Maple, Mathematica or MATLAB

Your engine, your dialect, and a workspace around them.

Within the ExaktAI Workspace, the Maple dialect on the Maple engine is Maple sent to Maple; the Mathematica dialect on the Mathematica engine is Wolfram Language sent to the Wolfram engine; the MATLAB dialect on the MATLAB engine is MATLAB sent to MATLAB. The Workspace drives the copy installed on your computer.

Two ExaktAI Workspace documents side by side: on the left a Maple worksheet on Lagrangians in rotating frames, chip reading maple to maple, with vector results carrying equation labels that later lines reference; on the right a Mathematica notebook on classical mechanics, chip reading mathematica to mathematica, ending in a three-dimensional trajectory plotted by the Wolfram engine — **maple → maple** on the left, **mathematica → mathematica** on the right, running with dialect and engine the same, on the copies installed on your computer.

All your work in progress, kept

Keep a dozen investigations going at once, and have only the ones you need in front of you.

Mathematical work is often several investigations in flight at once: the one you are on, the three you will come back to, the one from last month whose result you now need. The Workspace keeps them as a collection, outputs and context included. Close it and open it again: every document is where you left it, the unsaved ones included, at the line you were editing. Search across the text and the inputs of everything open, filter, bookmark, and put only what you need on the tab bar without discarding the rest.

Two ExaktAI Workspace windows: on the left a Maple document on the retarded and Lienard-Wiechert potentials with the screen split and the workspace panel open, listing five documents as cards with their dialect, whether each is Edited or Saved, and when it was last touched, above a search box and filters by time, engine and state; on the right the NumPy 101 tutorial — An afternoon's collection, on the left, its document split: the part being read on top, the part being written below, each scrolling on its own. Every open document is a card carrying its dialect, its state and when it was last touched, over a search that reads the text and the inputs of all of them.

Where validated AI mathematics lands

The Workspace is also the reading room for ExaktAI Validation.

When ExaktAI Validation validates an AI's solution, with SymPy, Maple or Mathematica, the result arrives here: an editable document holding the AI's reasoning as narrative and every computation as executable input, already run and already validated. Audit it, change a line, re-run it, extend it. Validated with Maple or Mathematica, the document is in that dialect, and the native .mw or .nb is written beside it.

On the left ExaktAI Validation, an ADMM problem answered by Codex and validated with SymPy in five and a half minutes; on the right the ExaktAI Workspace document that arrived from it, each step of the reasoning a paragraph of text followed by an executable input carrying its own computed result, down to the optimum at minus three and three — Where a validated run lands. ExaktAI Validation checked Codex's ADMM solution step by step with SymPy; the document that arrived from it holds every step as an executable input, so changing a line re-runs the derivation.

What it needs

SymPy, NumPy, SciPy and Matplotlib are bundled and run locally. Maple, Mathematica and MATLAB execution needs those products installed and licensed on your computer. Ordinary document and CAS work is local; no hosted AI is required to use the Workspace.

Translation between dialects covers mathematics, mappings and flow structures, not programs. It grows command by command, and not every command exists in all four systems. An imported document keeps its output without re-executing it, and anything the import cannot decode is kept untranslated. A document exported to another system preserves its contents, but may produce different results when run there.

Acknowledgments

The Workspace stands on open-source work: Python with SymPy, NumPy, SciPy and Matplotlib for the computing; Plotly for the plots; KaTeX and MathJax for the typesetting and MathLive for the formula editor; Tauri for the application itself; Hunspell and its dictionaries for the spelling. The three numerical tutorials were written with J.R. Johansson's Scientific Computing with Python lectures as their inspiration.

The full third-party notices →

Download the Beta

The Beta of the Workspace opens on September 9. You can pick your machine on the download page.

Download — Beta opens Sep 9

ExaktAI Validation

Its Beta is scheduled for the end of September 2026. A question, or a mathematical problem you would like to see it try? Write it here.

Your address is used only to answer you. No tracking, no mailing list, and it is never shared. Privacy policy →

^* SymPy, NumPy, SciPy and Matplotlib are trademarks of NumFOCUS, Inc., used here to identify the bundled software. ExaktAI is an independent product, not affiliated with, endorsed by, or sponsored by these projects or NumFOCUS. ↩

Maple is a trademark of Waterloo Maple Inc., Mathematica and Wolfram Language of Wolfram Research, Inc., and MATLAB of The MathWorks, Inc., used here to identify the software the Workspace works with. ExaktAI is an independent product, not affiliated with, endorsed by, or sponsored by them.