Source: https://seerepo.com/compare/lucidrains/PaLM-rlhf-pytorch/vs/onyx-dot-app/onyx
Markdown source: https://seerepo.com/compare/lucidrains/PaLM-rlhf-pytorch/vs/onyx-dot-app/onyx.md
Description: PaLM-rlhf-pytorch and onyx share 4 technologies: torch, einops, accelerate, and beartype. Both are written in Python.

# PaLM-rlhf-pytorch vs onyx

PaLM-rlhf-pytorch and onyx share 4 technologies: torch, einops, accelerate, and beartype. Both are written in Python.

- [lucidrains/PaLM-rlhf-pytorch](https://seerepo.com/r/lucidrains/PaLM-rlhf-pytorch): Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
- [onyx-dot-app/onyx](https://seerepo.com/r/onyx-dot-app/onyx): Open Source AI Platform - AI Chat with advanced features that works with every LLM

## What they share and what sets them apart

- In common: torch, einops, accelerate, beartype
- Only in PaLM-rlhf-pytorch: einx
- Only in onyx: FastAPI, amqp, asyncpg, azure-storage-blob, azure-storage-file-datalake, boxsdk, fastavro, google-cloud-core, ldap3, OpenSearch, partd, psycopg2-binary, py-key-value-aio, pyzmq, s3transfer, zict, Celery, Redis, Postgres, pyairtable, Sentry, Google, Google Cloud Storage, Hugging Face, OpenAI, PostHog, Stripe, asgiref, fastmcp-slim, Flask, graphql-core, jupyter-core, tornado, werkzeug, Terraform, starlette, AIOHTTP, fastmcp, uvicorn, anyio, React, Vite, Tauri, @tauri-apps/api, Tokio, objc2-app-kit, objc2-foundation, react-native, Expo, expo-secure-store, react-native-mmkv, Next.js, Lit, cycler, fonttools, soupsieve, charm.land/lipgloss/v2, contourpy, matplotlib-inline, prompt-toolkit, Rich, urwid, charm.land/bubbletea/v2, charm.land/bubbles/v2, charm.land/wish/v2, SQLAlchemy, alembic, fastapi-users-db-sqlalchemy, argon2-cffi, argon2-cffi-bindings, authlib, azure-identity, google-auth-httplib2, itsdangerous, joserfc, keyring, libpass, msal-extensions, pwdlib, pyjwt, python3-saml, fastapi-users, google-auth, cryptography, httpx-oauth, msal, oauthlib, requests-oauthlib, google-auth-oauthlib, agent-client-protocol, azure-cognitiveservices-speech, langchain-protocol, langsmith, NVIDIA, nvidia-cudnn-cu12, onnxruntime, openinference-instrumentation, openinference-semantic-conventions, scikit-learn, triton, litellm, MCP, chonkie, sentence-transformers, tiktoken, braintrust, langfuse, cohere, exa-py, LangChain, safetensors, tokenizers, transformers, unstructured-client, voyageai, chevron, courlan, defusedxml, docutils, et-xmlfile, jinja2, justext, lxml, lxml-html-clean, magika, mako, mammoth, markdown-it-py, markdownify, markupsafe, mdurl, msoffcrypto-tool, mwparserfromhell, olefile, pdfminer-six, pdfplumber, python-docx, python-pptx, rich-rst, ruamel-yaml, xlrd, xlsxwriter, beautifulsoup4, puremagic, pillow, github.com/yuin/goldmark, pypdf, pypdfium2, markitdown, mistune, openpyxl, reportlab, sendgrid, annotated-types, jsonschema-path, jsonschema-specifications, openapi-pydantic, referencing, validate, Pydantic, github.com/hashicorp/terraform-plugin-framework-validators, email-validator, azure-core, coloredlogs, execnet, OpenTelemetry, opentelemetry-exporter-http-transport, opentelemetry-exporter-otlp-common, opentelemetry-semantic-conventions, python-json-logger, supervisor, prometheus-client, psutil, boto3, botocore, prometheus-fastapi-instrumentator, github.com/sirupsen/logrus, kubernetes, aiobotocore, docker, github.com/charmbracelet/log, Prometheus, Tailwind CSS, rfd, tauri-nspanel, tauri-plugin-window-state, log, gtk, window-vibrancy, nativewind, class-variance-authority, tailwind-merge, react-native-svg, react-native-safe-area-context, rn-primitives, expo-image, React Hook Form, react-native-reanimated, react-native-gesture-handler, react-native-keyboard-controller, expo-splash-screen, expo-status-bar, react-native-enriched-markdown, Shopify, expo-document-picker, expo-image-picker, react-native-streamdown, next-themes, Formik, Radix UI, motion, react-dropzone, dnd-kit, lowlight, recharts, react-icons, Lucide, react-markdown, remark-gfm, highlight.js, rehype-katex, remark-math, katex, rehype-highlight, unified, docx-preview, dompurify, pdfjs-dist, react-pdf, rehype-sanitize, rehype-stringify, remark, remark-parse, xlsx, yup, TanStack, @floating-ui/react-dom, react-day-picker, marked

## Side by side

| | PaLM-rlhf-pytorch | onyx |
|---|---|---|
| Size | 3,612 lines written, 13 code files | 1,837,249 lines written, 4,192 code files |
| Who writes it | 0% of its commits signed by AI | 13.1% of its commits signed by AI. With Claude Code, Devin, Cursor, CodeRabbit, GitHub Copilot, and Sweep |
| Activity | Last push September 20, 2026, 157 commits, 7,863 stars | Last push November 19, 2026, 11,808 commits, 33,467 stars |
| Tests | 0 test files | 3,496 test files. 47.9% 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, PaLM-rlhf-pytorch or onyx?

onyx, with 1,837,249 lines written; PaLM-rlhf-pytorch has 3,612.

The proof: [onyx-dot-app/onyx's code at commit ffc1881](https://github.com/onyx-dot-app/onyx/tree/ffc18812a3d4ef954b090d51f6b413b4a69eae3f)

### Which has more GitHub stars, PaLM-rlhf-pytorch or onyx?

onyx, with 33,467 stars; PaLM-rlhf-pytorch has 7,863.

The proof: [onyx-dot-app/onyx on GitHub](https://github.com/onyx-dot-app/onyx)

### Which has more tests, PaLM-rlhf-pytorch or onyx?

onyx, with 3,496 test files.

The proof: [onyx-dot-app/onyx's code at commit ffc1881](https://github.com/onyx-dot-app/onyx/tree/ffc18812a3d4ef954b090d51f6b413b4a69eae3f)

### Which was updated more recently, PaLM-rlhf-pytorch or onyx?

onyx: its last push was on November 19, 2026, and PaLM-rlhf-pytorch's on September 20, 2026.

The proof: [onyx-dot-app/onyx's commits on GitHub](https://github.com/onyx-dot-app/onyx/commits)

### Which has more commits signed by AI, PaLM-rlhf-pytorch or onyx?

onyx: an AI signed 13.1% of its commits, with Claude Code, Devin, Cursor, CodeRabbit, GitHub Copilot, and Sweep.

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

## Sources

- lucidrains/PaLM-rlhf-pytorch: Read on November 18, 2026, at commit 68d712d (https://github.com/lucidrains/PaLM-rlhf-pytorch/tree/68d712dbd688edb4f1fd2f9b3f1d24d824f4bbeb)
- onyx-dot-app/onyx: Read on November 19, 2026, at commit ffc1881 (https://github.com/onyx-dot-app/onyx/tree/ffc18812a3d4ef954b090d51f6b413b4a69eae3f)

## 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.
