Skip to content
Kandang

A throwaway Linux box for your AI agent

Your agent sends code and files, and gets the output back.

See the API →
Measured on a Mac mini M4: a sandbox starts in 25 to 36 ms, and a pandas chart over 500,000 rows takes about 3.5 s.

What runs inside can’t get out

  • Open a socket→ Network unreachable
  • Allocate 2 GB under the 1 GB cap→ Killed
  • Spin in a busy loop→ Stopped at its timeout
  • Look for an API key→ None here, keys stay in your agent
  • gVisor kernel
  • Read-only root
  • Non-root user
  • No capabilities
  • Own CPU and process caps

Small and quick

Measured on a Mac mini M4.

Start a sandbox
25–36ms
Light Python job, 50 MB
0.6s
pandas chart over 500,000 rows, 225 MB
3.5s
12 MP photo edit, 145 MB
0.4s

One endpoint

Runs as one small Go service on any Linux host with gVisor.

POST /v1/runs
Authorization: Bearer <token>
In
Python or bash
Input files
Out
stdout and stderr
Charts, xlsx, pdf, docx, photos

Inside the image · Alpine · about 170 MB

  • bash
  • Python
  • numpy
  • pandas
  • matplotlib
  • Pillow
  • openpyxl
  • pypdf
  • python-docx
  • requests

Kandang is Indonesian for a pen

Built first for Palui