Comparison · Build it yourself
Curiosity and Amazon Neptune
Managed storage, or a managed context layer
Curiosity gives you a finished context layer; Neptune gives you a managed graph store.
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.
Amazon Neptune
A managed graph database on AWS supporting property graph queries with Gremlin and openCypher, and RDF with SPARQL. It suits teams already building on AWS, and is a storage and query layer rather than a finished product.
How Curiosity compares
Where the boundary falls
Neptune removes the work of operating a graph database. It does not remove the work of filling one, keeping it current and enforcing who may see what.
A finished layer, not a database
A graph store gives you somewhere to put the data. Curiosity ships the connectors, the enrichment, the retrieval and the permissions on top of it.
Weeks, not a modeling program
Building a context layer on raw graph infrastructure is a project measured in quarters and staffed with ontology expertise.
Search and AI included
Hybrid retrieval and model routing come with the system rather than being the next two things to integrate.
Side by side
Feature comparison
The same five questions, answered for both.
Deployment
Cloud or self-hosted, ready to use
AWS managed
Data model
Managed context layer and knowledge graph
Graph store with Gremlin, openCypher, SPARQL
Industrial fit
Built for industrial and enterprise teams
General purpose
Data reach
70+ systems connected, and yours through a connector you write
Whatever you load
Residency
EU hosted, or entirely your own infrastructure
AWS regions
Customization
What your team can change
Your own code, interface, data model and configuration. Amazon Neptune as its own documentation described it in October 2026. Where it says Not available, the vendor documents no such capability.
Your own code
C# endpoints, AI tools and tasks, compiled in Studio
Not available
Your own interface
Your own front end in C#, deployed from git
Not available
Data model
Typed node and edge schemas you define
Schema free property graph or RDF
Configuration as code
Every change committed to git, pushed to your remote
CloudFormation templates for clusters
APIs and SDKs
REST API, C# and Python library, connector SDK
Data API in AWS SDKs, Gremlin, openCypher, SPARQL
AI integration
What AI can build and reach
Whether AI can build on it, who reviews the result, and which models it runs. Amazon Neptune as its own documentation described it in October 2026.
AI that builds
Sudo drafts endpoints, tools, schemas and screens
Not available
Review before it applies
Every change a diff a person approves, in a sandbox
Not available
Model choice
Any major provider, or an OpenAI compatible endpoint
Bedrock foundation models for GraphRAG
Models on your servers
Open weights on your servers, or air gapped
Not available
Assistant permissions
Built in tools search as the user, per record
IAM role of the knowledge base or MCP server
Agent protocols
MCP server and an OpenAI compatible API
AWS Labs MCP server for queries and schema
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
Build it yourself
Other comparisons in this group
Neo4j
Curiosity gives you a finished context layer; Neo4j gives you a graph database.
CompareGraphwise GraphDB
Curiosity gives you a finished context layer; GraphDB gives you a semantic database.
CompareStardog
Curiosity gives you a finished context layer; Stardog gives you a semantic engine to model.
CompareYour data. Your infrastructure.