ray vs Agent-S
ray and Agent-S share 11 technologies: FastAPI, Google, uvicorn, tiktoken, scikit-learn, imageio-ffmpeg, lxml, pillow, beautifulsoup4, Pydantic, and boto3. Both are written in Python.
LinkedInWhat they share and what sets them apart
ray-project
ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Python44.2kRead on November 6, 2026, at commit 77567c5What is ray built with?Only in ray
- amqp
- async-lru
- azure-common
- azure-datalake-store
- azure-storage-blob
confluent-kafka
- diskcache
expiringdict
- gitdb
google-cloud-core
h5py
kombu
pickleshare
- pylance
- pymongo
pyarrow
- aioboto3
- MongoDB
- Redis
- adlfs
- smart-open
pyiceberg
- pymysql
clickhouse-connect
deltalake
- gcsfs
- Celery
- fastavro
- pyzmq
- s3fs
webdataset
- Hugging Face
- Google Cloud Storage
- Kafka
- asgiref
- Flask
- flask-cors
- graphene
- graphql-core
graphql-relay
- jupyter-core
jupyterlab-server
werkzeug
- Ray
starlette
- AIOHTTP
- Lightning
- anyio
tornado
- React
react-router-dom
- alabaster
- cycler
fonttools
jupyterlab-pygments
pydata-sphinx-theme
- soupsieve
sphinx-design
- tinycss2
contourpy
- glfw
- jupyter-server-terminals
- jupyterlab-widgets
- matplotlib-inline
- Plotly
prompt-toolkit
pyopengl
- Textual
- widgetsnbextension
- xyzservices
- Gradio
- ipywidgets
matplotlib
- Rich
- pydot
- alembic
peewee
sqlglot
- SQLAlchemy
- argon2-cffi
- argon2-cffi-bindings
- azure-identity
- flask-basicauth
itsdangerous
joserfc
- jwcrypto
- keyring
- msal
- msal-extensions
- oauth2client
oauthlib
- pyjwt
requests-oauthlib
- cryptography
- albucore
- bitsandbytes
cmdstanpy
- crcmod
cupy-cuda12x
- einops
- fairscale
gradio-client
- gym
- LangChain
- llvmlite
lm-eval
- ml-dtypes
- MLflow
nltk
- ONNX
- onnxruntime
onnxscript
openai-whisper
- opt-einsum
- orbax-checkpoint
peft
prophet
rouge-score
- sacrebleu
safetensors
scikit-image
- sentencepiece
skops
tf-keras
timm
tokenizers
torchtext
- triton
- gymnasium
- torch
- transformers
- TensorFlow
jax
torchvision
- xgboost
lightgbm
accelerate
- datasets
- pytorch-lightning
evaluate
flax
- Keras
- torchmetrics
albumentations
deepspeed
diffusers
- hyperopt
- Optuna
- pettingzoo
tensordict
tensorflow-datasets
tensorflow-probability
torchaudio
- bleach
- defusedxml
et-xmlfile
imageio
- imagesize
- jsonlines
- linkify-it-py
- mako
- markdown
markdown-it-py
markupsafe
- mdurl
mistune
- moviepy
- nbconvert
- nh3
- openpyxl
- pandocfilters
ruamel-yaml
webencodings
- xlrd
- xmltodict
- docutils
- jinja2
av
- nbformat
- torchcodec
- annotated-types
- fastjsonschema
- fqdn
- jsonschema-specifications
- pathvalidate
- pydantic-core
- referencing
- rfc3339-validator
- rfc3986
- rfc3986-validator
- validators
- jsonschema
- openapi-schema-validator
- aiobotocore
- azure-mgmt-compute
- azure-mgmt-resource
- colorlog
- Gunicorn
- opentelemetry-api
opentelemetry-instrumentation
- opentelemetry-semantic-conventions
- python-json-logger
psutil
- botocore
prometheus-client
- OpenTelemetry
kubernetes
opentelemetry-exporter-prometheus
- docker
- typeface-roboto
- MUI
usehooks-ts
- lowlight
react-window
react-icons
- @mui/icons-material
- js-yaml
In common
simular-ai
Agent-S
Agent S: the state-of-the-art open source computer use agents
Python12.9kRead on November 10, 2026, at commit 0fff0e6What is Agent-S built with?Only in Agent-S
Side by side
rayAgent-S
SizeLines written by people and agents, without generated ones; code files, without tests.
ray1,531,664 lines written2,777 code files
Agent-S55,076 lines written135 code files
Who writes itA commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
ray3.6% of its commits signed by AIWith Claude Code, Gemini CLI, GitHub Copilot, Cursor, and Codex
Agent-S5.1% of its commits signed by AIWith Claude Code and Cursor
ActivityFrom GitHub and its history, on the day SeeRepo read it.
rayLast push November 6, 202632,373 commits44,213 stars
Agent-SLast push October 30, 2026315 commits12,922 stars
TestsThe files that test the code, and the share of code files a test imports.
ray2,168 test files9.7% of its code files have a test that imports them
Agent-S80 test files37% of its code files have a test that imports them
Frequently asked questions
Which is bigger, ray or Agent-S?
ray, with 1,531,664 lines written; Agent-S has 55,076.
The proof: ray-project/ray's code at commit 77567c5
Which has more GitHub stars, ray or Agent-S?
ray, with 44,213 stars; Agent-S has 12,922.
The proof: ray-project/ray on GitHub
Which has more tests, ray or Agent-S?
ray, with 2,168 test files; Agent-S has 80.
The proof: ray-project/ray's code at commit 77567c5
Which was updated more recently, ray or Agent-S?
ray: its last push was on November 6, 2026, and Agent-S's on October 30, 2026.
The proof: ray-project/ray's commits on GitHub
Which has more commits signed by AI, ray or Agent-S?
Agent-S: an AI signed 5.1% of its commits, with Claude Code and Cursor; in ray, 3.6%.
See inside your code, today.
Paste your repo and see it drawn, part by part: a medium one in under a minute.
Free, no account.
