Every raw model response is publicly verifiable
Download image (with QR code)Share on XShare on LinkedIn

WeChat: save the image and long-press the QR code in a chat.

← Back to all rankings

Most Popular Code Execution Sandboxes for AI Agents

ai-tooling12 models · updated 08/31/2026, 10:48 PM

Most Popular Code Execution Sandboxes for AI Agents

Share
Download image (with QR code)Share on XShare on LinkedIn

WeChat: save the image and long-press the QR code in a chat.

Brand Index
  • 1E2B86.98
  • 2Docker75.25
  • 3Modal69.41
  • 4Replit51.00
  • 5Daytona40.64
  • 6CodeSandbox30.03
  • 7Firecracker25.28
  • 8Fly.io19.80
  • 9OpenAI18.59
  • 10AWS Lambda13.79
  • 11Runloop11.17
  • 12gVisor10.32
  • 13Jupyter10.18
  • 14Cloudflare10.09
  • 15Kubernetes6.82
  • 16Google Colab6.78
  • 17Fireworks AI6.03
  • 18StackBlitz5.24
  • 19Judge05.19
  • 20Google Cloud4.49
  • 21Piston4.40
  • 22Azure Functions3.85
  • 23Riza3.52
  • 24Northflank3.45
  • 25Azure Container Instances3.39
  • 26Anthropic3.11
  • 27Kata Containers3.11
  • 28Google2.76
  • 29Microsoft2.42
  • 30Amazon2.07
  • 31IBM1.73
  • 32Google Cloud Run1.47
  • 33Meta1.38
  • 34Deno1.28
  • 35Alibaba1.04
  • 36GitHub Codespaces0.86
  • 37Pyodide0.85
  • 38Baidu0.69
  • 39WasmEdge0.64
  • 40Gitpod0.59
  • 41Tencent0.35
Trend Across Runs
  • E2B
  • Docker
  • Modal
  • Replit
  • Daytona
  • CodeSandbox
02040608010008/31 15:5708/31 22:48E2BDockerModalReplitDaytonaCodeSandbox

You can also query this data from Claude, Cursor or another agent, with the same reading rules attached. For agents →