Code execution sandboxes
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | territory of the AI industry |
|---|---|
| Categories | 6 |
| Companies | 31 |
| Map last changed | 2026-11-19 |
| Map | open the map |
Code execution sandboxes is a territory of the AI industry on map of ai. In short: code execution sandboxes run untrusted code in isolated environments with controlled resource limits and system access. The map lists 31 products and companies in 6 categories.
The map of code execution sandboxes has 6 categories. Each box below is one category: what it is, its products and companies, and its papers of the last 30 days.
sandbox infrastructure for agents6 products and companies
Code execution sandboxes provide isolated runtime environments where untrusted or experimental code runs without access to the host system. Developers, AI platforms, and security researchers use them to safely execute scripts, test code, and run agent workloads.
Products and companies
Open ground
Docker and gVisor provide container sandboxing, Firecracker offers lightweight VMs, and Anthropic runs sandboxed code execution for Claude; none of them ship a unified platform that bundles sandboxing, networking isolation, and persistent state management across distributed execution nodes.
microvm and isolation runtimes5 products and companies
Microvm and isolation runtimes execute untrusted code in lightweight virtual machines or sandboxed processes, isolating it from the host system. Used by cloud platforms, serverless providers, and security researchers to run code with bounded resource access and limited blast radius.
Products and companies
cloud dev environments6 products and companies
Cloud dev environments are hosted IDEs and coding workspaces that execute code in the browser or remotely, used by individual developers and teams to write, test, and run code without local setup. They provide real-time collaboration, pre-configured runtimes, and instant access to computing resources.
Products and companies
notebook and data analysis sandboxes5 products and companies
Notebook and data analysis sandboxes let data scientists, researchers, and analysts write code in cells, visualize outputs, and explore datasets interactively in a browser. Users run Python, R, SQL, and other languages against live data without managing infrastructure.
Products and companies
built-in model code interpreters4 products and companies
Built-in code interpreters execute code snippets within development environments and notebooks without requiring external setup. Data scientists, developers, and AI researchers use them to run Python, JavaScript, and other languages inline within their tools.
Products and companies
browser sandboxes for agents5 products and companies
Browser sandboxes for agents run untrusted code in isolated browser environments, typically used by AI agents, automation platforms, and security researchers to execute web interactions safely. They provide headless or visible browser instances with network isolation, filesystem restrictions, and resource limits.
Products and companies
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.