Skip to main content
idapt
AccueilCodeModèles IATarifs
Sign inStart free
All features

Compute

Cloud code execution that actually runs.

Sandboxed Python, Node, and shell: agents and you, side-by-side.

Try nowSee pricing

Three languages, ready.

Anything you'd normally install just works.

Python

for data, charts, and most everything

Node.js

for web and API work

Shell

for files and quick scripts

Fresh start each time

Every run starts clean. Nothing leftover from before, nothing from anyone else.

Safe by default

Runs in its own little box. Only reaches outside when you gave the agent permission (like web search).

Results saved properly

Charts, files, anything it makes lands in your Drive as a real file you can keep, share, or roll back.

Versus ChatGPT's code mode

ChatGPT's code runner is one chat at a time and the outputs vanish with it. Here, code runs against the files in your Drive and the results land back as real files you can keep using.

What you get

Disposable sandboxes

Every run starts in a clean environment. No leftover state, no surprises from prior sessions.

Python, Node, shell

Three runtimes ship by default. Pip / npm install whatever you need on the fly.

Read your real files

Mount idapt folders into the sandbox so generated scripts work against actual data, not toy examples.

Capture every artifact

Files written during execution land back in your workspace, versioned, with a trace of which run produced them.

Agents run code, you watch

When an agent needs to compute, it executes here. You see the script, the output, and can re-run it yourself.

Who it's for

Data analysts

Drop in a CSV, ask for the pivot you need, get a chart and the pandas snippet that produced it.

Developers

Prototype a function, run a test against staging data, refine without touching your local env.

Researchers

Reproduce a paper's numerical result: the sandbox makes it copy-and-rerun, not download-and-pray.

How it works

  1. 1
    Ask

    Describe the computation in chat or give an agent the goal.

  2. 2
    Run

    The model writes code; the sandbox executes it; you see the output inline.

  3. 3
    Iterate

    Tweak the request: the run is fast and disposable, so failed attempts cost nothing.

  4. 4
    Keep what works

    Save the script to a folder, schedule it, or hand it to an agent for repeat runs.

Frequently asked

Drop a spreadsheet. Ask a question.

The AI runs the numbers. You get the chart and the script behind it.

Try itRead the docs

Read the docs

  • Code execution overview

Pair with

  • Computers
  • Agents
  • Automations
  • Accueil
  • Tarifs
  • Modèles IA
  • Modèles d'image
  • Modèles de voix
  • Modèles vidéo
  • Classements
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Bientôt
  • Containers · Bientôt
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Cas d'usage
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Centre d'aide
  • FAQ
  • Confidentialité
  • Comparer tous les modèles
  • Support
  • idapt Code
  • Développeurs
  • Quickstarts
  • Référence API
  • Tarifs API
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]ConditionsPolitique de confidentialitéMentions légalesSignaler un contenu
X (Twitter)