Heads up This site is currently under heavy development.
← all datasets
◆ Evals & benchmarks

OSWorld

Apache-2.0

Open-ended computer-use tasks in real Ubuntu and Windows desktops, each with an execution-based check (NeurIPS 2024).

Summary

Formats
json
License
Apache-2.0
Added
2026-09-10

Get it

From the project’s own instructions where it documents any; otherwise a plain clone.

  1. shell
    $ git clone https://github.com/xlang-ai/OSWorld
  2. shell
    $ cd OSWorld && pip install desktop-env

    Tasks run in a full VM (VMware, VirtualBox, Docker with KVM, or a cloud provider).

Contents

1,190 files 121.9 MB repository

  • .py 619
  • .json 440
  • .md 38
  • .png 33
  • .txt 22
  • (no ext) 10
  • .sh 8
  • .css 3

Use it with

Commands are curated, not yet run by us.

jq — Stream the records one per line to see their shape.

sample.json
$ jq -c . sample.json

DuckDB — Query the file in place with SQL — DuckDB detects CSV, JSON and JSONL by extension.

sample.json
$ duckdb -c 'SELECT * FROM '\''sample.json'\'' LIMIT 10'
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →

    Send us feedback