curiosity

Comparison · AI assistants

Curiosity and Onyx
Chat over documents, or a graph of records

Curiosity models industrial records into a graph; Onyx is an open source assistant over your documents.

Their deployment Self-hosted or vendor cloud Their data model Search and chat over documents Our deployment Cloud or your own servers Our residency EU, or your own

Your data · your environment

Who each tool is for

Different problems, honestly stated

Curiosity

For industrial and regulated teams whose knowledge sits in engineering systems and structured records, where the answer depends on how those records connect, and where the deployment has to run on their own infrastructure.

Onyx

An open source AI assistant and enterprise search, formerly Danswer, that you can host yourself or use as a cloud service, with a choice of models and connectors to common workplace tools. It suits engineering teams that want chat over company documents on their own servers and are happy to run it.

How Curiosity compares

Where the boundary falls

Onyx and Curiosity both run on your infrastructure with the model you choose, and both can be tried for free. The difference is underneath: Onyx retrieves passages from your documents, Curiosity models the entities and relationships across your records and builds tools on them.

Built for the industrial estate

General assistants are tuned for cloud collaboration tools. Curiosity connects engineering systems, data lakes, network drives and proprietary sources.

Structured context, not a chat layer

The graph models entities and relationships, so answers reason over how records connect rather than over retrieved passages.

On your infrastructure

On premises or private cloud, with data residency you control and the model of your choice.

Side by side

Feature comparison

The same five questions, answered for both.

QuestionCuriosityOnyx

Deployment

Cloud or self-hosted, ready to use

Self-hosted or vendor cloud

Data model

Managed context layer and knowledge graph

Search and chat over documents

Industrial fit

Built for industrial and enterprise teams

Teams that run their own tools

Data reach

70+ systems connected, and yours through a connector you write

Workplace tool connectors

Residency

EU hosted, or entirely your own infrastructure

Your choice

Customization

What your team can change

Your own code, interface, data model and configuration. Onyx as its own documentation described it in October 2026. Where it says Not available, the vendor documents no such capability.

QuestionCuriosityOnyx

Your own code

C# endpoints, AI tools and tasks, compiled in Studio

Open source code, HTTP hook extensions in Enterprise

Your own interface

Your own front end in C#, deployed from git

Open source front end, website widget, white labeling

Data model

Typed node and edge schemas you define

Not available

Configuration as code

Every change committed to git, pushed to your remote

Deployment as Helm, Terraform and env files

APIs and SDKs

REST API, C# and Python library, connector SDK

REST API, ingestion API, CLI

AI integration

What AI can build and reach

Whether AI can build on it, who reviews the result, and which models it runs. Onyx as its own documentation described it in October 2026.

QuestionCuriosityOnyx

AI that builds

Sudo drafts endpoints, tools, schemas and screens

Craft builds web apps and dashboards from a prompt

Review before it applies

Every change a diff a person approves, in a sandbox

Craft runs in a sandbox, actions ask by policy

Model choice

Any major provider, or an OpenAI compatible endpoint

OpenAI, Anthropic, Azure, any OpenAI compatible endpoint

Models on your servers

Open weights on your servers, or air gapped

Self hosted, local models via Ollama

Assistant permissions

Built in tools search as the user, per record

Permission sync from sources, Enterprise Edition

Agent protocols

MCP server and an OpenAI compatible API

MCP client and server, OpenAI compatible gateway

At Airbus, we developed the next generation of customer support AI assistance tools with Curiosity, enhancing our technical support’s ability to access and navigate vast data from multiple sources, including millions of documents.

Services Innovation Team

Airline Services at Airbus

Your data. Your infrastructure.

Connected knowledge for AI systems