Skip to content

Overview

Commit-0 is a from scratch AI coding challenge. Can you create a library from commit 0?

The benchmark consists of 54 core Python libraries. The challenge is to rebuild these libraries and pass their unit tests. All libraries have:

  • Significant test coverage
  • Detailed specification and documentation
  • Lint and type checking

Commit-0 is an interactive environment that makes it easy to design and test new agents. You can:

  • Efficiently run tests in isolated environments
  • Distribute testing and development across cloud systems
  • Track and log all changes made throughout.

To install run:

pip install commit0

Architecture

Libraries

Name Repo Commit0 Tests
minitorch [orig] [commit0] 230
simpy [orig] [commit0] 140
bitstring [orig] [commit0] 834
tinydb [orig] [commit0] 201
marshmallow [orig] [commit0] 1229
python-prompt-toolkit [orig] [commit0] 151
parsel [orig] [commit0] 343
pyjwt pyjwt [orig] [commit0] 259
networkx [orig] [commit0] 5440
graphene [orig] [commit0] 447
tlslite-ng tlslite-ng [orig] [commit0] 1653
wcwidth wcwidth [orig] [commit0] 38
chardet chardet [orig] [commit0] 376
dnspython dnspython [orig] [commit0] 1304
imapclient imapclient [orig] [commit0] 267
virtualenv [orig] [commit0] 284
pexpect pexpect [orig] [commit0] 255
web3.py [orig] [commit0] 40433
babel [orig] [commit0] 5663
geopandas [orig] [commit0] 2196
dulwich dulwich [orig] [commit0] 1522
flask [orig] [commit0] 477
voluptuous voluptuous [orig] [commit0] 149
jinja [orig] [commit0] 851
seaborn [orig] [commit0] 2362
requests requests [orig] [commit0] 590
scrapy [orig] [commit0] 2904
fastapi [orig] [commit0] 2013
click [orig] [commit0] 589
python-rsa [orig] [commit0] 86
statsmodels [orig] [commit0] 17669
more-itertools more-itertools [orig] [commit0] 662
moviepy [orig] [commit0] 109
deprecated deprecated [orig] [commit0] 171
pydantic [orig] [commit0] 5091
loguru [orig] [commit0] 1461
pypdf [orig] [commit0] 911
attrs [orig] [commit0] 1414
mimesis [orig] [commit0] 6159
cookiecutter [orig] [commit0] 367
tornado [orig] [commit0] 1150
imbalanced-learn [orig] [commit0] 2310
python-progressbar [orig] [commit0] 385
PyBoy [orig] [commit0] 201
pytest [orig] [commit0] 3612
pylint [orig] [commit0] 1878
sphinx [orig] [commit0] 2187
joblib [orig] [commit0] 1450
xarray [orig] [commit0] 15643
cachetools cachetools [orig] [commit0] 215
paramiko paramiko [orig] [commit0] 557
fabric [orig] [commit0] 353
filesystem_spec [orig] [commit0] 698
jedi jedi [orig] [commit0] 3854
sqlparse sqlparse [orig] [commit0] 461
portalocker [orig] [commit0] 38