Skip to main content

​
Deployment Modes

Onyx supports two deployment modes: Onyx Standard — The full Onyx platform, recommended for serious users and larger teams. Includes everything in Lite plus:
  • Vector + Keyword index for RAG
  • Background containers for syncing knowledge from connectors
  • AI model inference servers for deep learning models used during indexing and inference
  • File storage in the object store
  • Performance optimizations via Redis
Onyx Lite — A lightweight Chat UI that uses fewer resources than Onyx Standard. It is great for users who want to try Onyx quickly or teams only interested in Chat and Agents. Includes LLM chat, tools, file uploads, and Projects, but does not use the vector database or background workers. Docker Compose Lite skips both model servers; Helm Lite still starts the inference model server unless you disable it explicitly.
Onyx Lite does not include indexing. Use Onyx Standard to index knowledge from connected applications.

​
Quickstart

Install Script (Recommended)

A guided installation script that deploys Onyx in Docker Compose. Supports both Standard and Lite modes.

​
Resourcing

Resourcing Guide

Resource requirements, cloud instance selection, and scaling guidance for your Onyx deployment.

​
Deployment Options

Onyx provides a flexible set of deployment options from self-hosted to fully managed.

Self-Host Open Source

Get all of Onyx’s core features, including Internal Search, Connectors, Chat, Agents, Actions, Deep Research, and more! All of your data remains secure within your Onyx deployment.For teams looking for a powerful free solution

Onyx Cloud

Onyx managed solution with all Enterprise Edition features. Comes with a 2 week free trial (no credit card needed)!SOC2 Type II and GDPR compliant.The most effortless way to get Onyx to your whole team

Self-Host Enterprise Edition

Self-Host with all premium features such as Role-Based Access Control (RBAC), automatic sync-ing of permission, and advanced knowledge curation options.Best for large teams with strict data requirements