Comparison · Data platforms
Curiosity and Palantir Foundry and AIP
A platform, or a layer
Curiosity gives you a focused context layer; Foundry and AIP are a full operating system.
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.
Palantir Foundry and AIP
A data operating system with strong ontology, integration and governance capabilities, with AIP for building AI applications and agents on that ontology, used for operational analytics at scale in industrial and defense settings. It is a broad platform, typically adopted through long programs led by professional services.
How Curiosity compares
Where the boundary falls
Foundry does far more than Curiosity does, and for organizations committing to it as their operating system that breadth is the point. If what you need is the context layer, it is a large way to buy one.
A focused layer, not an operating system
A full data platform is adopted through a long program. Curiosity does one thing, the context layer, and can be in production without one.
Open, not proprietary
Your model, your infrastructure, and a graph you can query from your own code rather than a proprietary ontology you adopt wholesale.
Without the services engagement
A free developer install and an evaluation your own engineers can run before anyone signs anything.
Side by side
Feature comparison
The same five questions, answered for both.
Deployment
Cloud or self-hosted, ready to use
Vendor cloud or on premises
Data model
Managed context layer and knowledge graph
Full data platform with ontology
Industrial fit
Built for industrial and enterprise teams
Industrial and defense, through long programs
Data reach
70+ systems connected, and yours through a connector you write
Broad, with services
Residency
EU hosted, or entirely your own infrastructure
Configurable
Customization
What your team can change
Your own code, interface, data model and configuration. Palantir Foundry and AIP 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
Python and TypeScript functions, transforms in repositories
Your own interface
Your own front end in C#, deployed from git
Workshop app builder, OSDK React apps, custom widgets
Data model
Typed node and edge schemas you define
Ontology object types, links and actions
Configuration as code
Every change committed to git, pushed to your remote
Git code repositories, Global Branching proposals
APIs and SDKs
REST API, C# and Python library, connector SDK
OSDK for TypeScript, Python and Java, OpenAPI
AI integration
What AI can build and reach
Whether AI can build on it, who reviews the result, and which models it runs. Palantir Foundry and AIP as its own documentation described it in October 2026.
AI that builds
Sudo drafts endpoints, tools, schemas and screens
AI FDE builds pipelines, ontology, functions and apps
Review before it applies
Every change a diff a person approves, in a sandbox
AI FDE proposes branch proposals or pull requests
Model choice
Any major provider, or an OpenAI compatible endpoint
OpenAI, Bedrock, Vertex, xAI, bring your own model
Models on your servers
Open weights on your servers, or air gapped
Self hosted models in compute modules, air gapped
Assistant permissions
Built in tools search as the user, per record
AI FDE respects users' existing permissions
Agent protocols
MCP server and an OpenAI compatible API
Palantir MCP, OpenAI compatible proxy endpoints
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
Data platforms
Other comparisons in this group
Databricks
Curiosity is a finished context layer; Databricks is a data platform to build agents on.
CompareSnowflake
Curiosity connects records where they live; Snowflake runs agents over the data in its cloud.
CompareDataiku
Curiosity is a context layer teams build on; Dataiku is a platform for data science and AI projects.
CompareYour data. Your infrastructure.