Source: https://seerepo.com/compare/LearningCircuit/local-deep-research/vs/ray-project/ray
Markdown source: https://seerepo.com/compare/LearningCircuit/local-deep-research/vs/ray-project/ray.md
Description: local-deep-research and ray share 44 technologies: anyio, FastAPI, gitdb, s3transfer, starlette, uvicorn, werkzeug, AIOHTTP, soupsieve, Rich, peewee, alembic, id, keyring, pyjwt, tiktoken, LangChain, docutils, markdown-it-py, mdurl, nh3, readme-renderer, ruamel-yaml, ruamel-yaml-clib, xmltodict, beautifulsoup4, defusedxml, jinja2, lxml, markupsafe, markdown, annotated-types, jsonschema, jsonschema-specifications, referencing, rfc3986, Pydantic, boto3, botocore, docker, OpenTelemetry, opentelemetry-instrumentation, opentelemetry-semantic-conventions, and opentelemetry-util-http. Both are written in Python.

# local-deep-research vs ray

local-deep-research and ray share 44 technologies: anyio, FastAPI, gitdb, s3transfer, starlette, uvicorn, werkzeug, AIOHTTP, soupsieve, Rich, peewee, alembic, id, keyring, pyjwt, tiktoken, LangChain, docutils, markdown-it-py, mdurl, nh3, readme-renderer, ruamel-yaml, ruamel-yaml-clib, xmltodict, beautifulsoup4, defusedxml, jinja2, lxml, markupsafe, markdown, annotated-types, jsonschema, jsonschema-specifications, referencing, rfc3986, Pydantic, boto3, botocore, docker, OpenTelemetry, opentelemetry-instrumentation, opentelemetry-semantic-conventions, and opentelemetry-util-http. Both are written in Python.

- [LearningCircuit/local-deep-research](https://seerepo.com/r/LearningCircuit/local-deep-research):  ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
- [ray-project/ray](https://seerepo.com/r/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.

## What they share and what sets them apart

- In common: anyio, FastAPI, gitdb, s3transfer, starlette, uvicorn, werkzeug, AIOHTTP, soupsieve, Rich, peewee, alembic, id, keyring, pyjwt, tiktoken, LangChain, docutils, markdown-it-py, mdurl, nh3, readme-renderer, ruamel-yaml, ruamel-yaml-clib, xmltodict, beautifulsoup4, defusedxml, jinja2, lxml, markupsafe, markdown, annotated-types, jsonschema, jsonschema-specifications, referencing, rfc3986, Pydantic, boto3, botocore, docker, OpenTelemetry, opentelemetry-instrumentation, opentelemetry-semantic-conventions, opentelemetry-util-http
- Only in local-deep-research: OpenAI, Bootstrap, Chart.js, chartjs-adapter-date-fns, chartjs-plugin-annotation, bootstrap-icons, Font Awesome, SQLAlchemy, ecdsa, langchain-openai, faiss-cpu, langchain-ollama, langchain-anthropic, crawl4ai, MCP, sentence-transformers, pdfplumber, pypdf, dompurify, extruct, highlight.js, html2canvas, jspdf, justext, katex, marked, marked-katex-extension, readabilipy, unstructured, beartype, schema, opentelemetry-instrumentation-requests, opentelemetry-instrumentation-threading, structlog
- Only in ray: aimrecords, aimrocks, amqp, array-record, arro3-core, async-lru, azure-common, azure-datalake-store, azure-storage-blob, confluent-kafka, delta-kernel-rust-sharing-wrapper, diskcache, expiringdict, feather-format, google-cloud-core, h5py, huey, jupyter-cache, kombu, partd, petastorm, pickleshare, py-partiql-parser, pylance, pymongo, qpd, s3torchconnectorclient, semidbm, sqlitedict, taskiq, tensorboard-data-server, zict, pyarrow, mcap, aioboto3, MongoDB, Redis, adlfs, pyiceberg, smart-open, clickhouse-connect, daft, deltalake, gcsfs, lance-namespace, obstore, Celery, delta-sharing, fastavro, hudi, pyzmq, s3fs, s3torchconnector, taskiq-redis, zarr, Google, Hugging Face, Google Cloud Storage, Kafka, Databricks, adagio, asgiref, Flask, flask-cors, graphene, graphql-core, graphql-relay, jupyter-core, jupyterlab-server, pygame, pymars, Ray, pyspark, Lightning, raydp, tornado, React, react-router-dom, accessible-pygments, alabaster, cycler, fonttools, jupyterlab-pygments, pydata-sphinx-theme, sphinx-design, tinycss2, aim-ui, alive-progress, bokeh, contourpy, glfw, halo, jupyter-server-terminals, jupyterlab-widgets, matplotlib-inline, Plotly, prompt-toolkit, pyglet, pyopengl, spinners, Textual, widgetsnbextension, xyzservices, Gradio, ipywidgets, pydot, sqlglot, adal, argon2-cffi, argon2-cffi-bindings, azure-identity, flask-basicauth, gcs-oauth2-boto-plugin, google-auth-oauthlib, google-oauth, google-reauth, itsdangerous, joserfc, jwcrypto, msal, msal-extensions, oauth2client, oauthlib, pyu2f, requests-oauthlib, cryptography, google-auth-httplib2, aws-requests-auth, albucore, autograd, ax-platform, bayesian-optimization, bitsandbytes, botorch, cma, cmdstanpy, crcmod, cupy-cuda100, cupy-cuda12x, cupy-cuda13x, einops, fairscale, fbgemm-gpu, gpytorch, gradio-client, gym, jaxlib, labmaze, lightning-utilities, linear-operator, llvmlite, lm-eval, minigrid, ml-dtypes, moocore, mosaicml, nltk, ONNX, onnx-ir, onnxruntime, onnxscript, openai-whisper, opt-einsum, optax, orbax-checkpoint, peft, prophet, pymoo, pyro-ppl, pytorch-ranger, rouge-score, sacrebleu, safetensors, scikit-image, sentencepiece, skops, stanio, statsforecast, tf-keras, timm, tokenizers, torch-geometric, torch-optimizer, torch-scatter, torch-sparse, torchtext, triton, yahp, gymnasium, torch, transformers, TensorFlow, jax, torchvision, xgboost, lightgbm, scikit-learn, MLflow, datasets, pytorch-lightning, comet-ml, dm-env, flax, Keras, torchmetrics, aim, ale-py, configspace, deepspeed, diffusers, dm-control, hpbandster, hyperopt, nevergrad, open-spiel, Optuna, tensorflow-probability, zoopt, bleach, et-xmlfile, imageio, imageio-ffmpeg, imagesize, jsonlines, linkify-it-py, mako, mdit-py-plugins, mistune, moviepy, myst-parser, nbconvert, openpyxl, pandocfilters, pytablewriter, strictyaml, tinyscaler, webencodings, xlrd, pillow, decord, nbformat, torchcodec, fastjsonschema, fqdn, jsonschema-path, openapi-spec-validator, pathvalidate, rfc3339-validator, rfc3986-validator, typepy, validators, aiobotocore, applicationinsights, aws-sam-translator, aws-xray-sdk, azure-cli-core, azure-cli-telemetry, azure-core, azure-mgmt-compute, azure-mgmt-core, azure-mgmt-network, azure-mgmt-resource, azure-mgmt-resource-deployments, boto, cloud-tpu-diagnostics, colorlog, execnet, google-cloud-audit-log, Gunicorn, log-symbols, ml-goodput-measurement, msrestazure, opencensus-context, opentelemetry-instrumentation-asgi, python-json-logger, supervisor, psutil, prometheus-client, pybuildkite, kubernetes, opentelemetry-exporter-prometheus, opentelemetry-exporter-otlp-proto-grpc, opentelemetry-instrumentation-fastapi, ray-haproxy, typeface-roboto, MUI, usehooks-ts, lowlight, react-window, react-icons, @mui/icons-material, js-yaml

## Side by side

| | local-deep-research | ray |
|---|---|---|
| Size | 1,820,812 lines written, 712 code files | 1,566,356 lines written, 2,810 code files |
| Who writes it | 1.2% of its commits signed by AI. With Claude Code, GitHub Copilot, Kilo Code, and Cursor | 3.7% of its commits signed by AI. With Claude Code, Gemini CLI, GitHub Copilot, Cursor, and Codex |
| Activity | Last push November 14, 2026, 7,056 commits, 9,582 stars | Last push November 13, 2026, 32,468 commits, 44,282 stars |
| Tests | 3,252 test files. 80.1% of its code files have a test that imports them | 2,208 test files. 9.4% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, local-deep-research or ray?

local-deep-research, with 1,820,812 lines written; ray has 1,566,356.

The proof: [LearningCircuit/local-deep-research's code at commit 3d6e615](https://github.com/LearningCircuit/local-deep-research/tree/3d6e6151cffdb8f8926567b700d538fcd69afb8c)

### Which has more GitHub stars, local-deep-research or ray?

ray, with 44,282 stars; local-deep-research has 9,582.

The proof: [ray-project/ray on GitHub](https://github.com/ray-project/ray)

### Which has more tests, local-deep-research or ray?

local-deep-research, with 3,252 test files; ray has 2,208.

The proof: [LearningCircuit/local-deep-research's code at commit 3d6e615](https://github.com/LearningCircuit/local-deep-research/tree/3d6e6151cffdb8f8926567b700d538fcd69afb8c)

### Which was updated more recently, local-deep-research or ray?

local-deep-research: its last push was on November 14, 2026, and ray's on November 13, 2026.

The proof: [LearningCircuit/local-deep-research's commits on GitHub](https://github.com/LearningCircuit/local-deep-research/commits)

### Which has more commits signed by AI, local-deep-research or ray?

ray: an AI signed 3.7% of its commits, with Claude Code, Gemini CLI, GitHub Copilot, Cursor, and Codex; in local-deep-research, 1.2%.

The proof: [the commits each tool signed in ray-project/ray](https://seerepo.com/r/ray-project/ray/ai)

## Sources

- LearningCircuit/local-deep-research: Read on November 14, 2026, at commit 3d6e615 (https://github.com/LearningCircuit/local-deep-research/tree/3d6e6151cffdb8f8926567b700d538fcd69afb8c)
- ray-project/ray: Read on November 13, 2026, at commit de4c576 (https://github.com/ray-project/ray/tree/de4c5765b6cf0265f43f9edccf5bd3821f3a9468)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.