Open data context for AI agents

The trusted enterprise data context for AI agents.

Connect business ontology, governed metrics, and data provenance in one shared context layer. Give agents business meaning they can use—and teams the evidence to inspect their work.
TerminalQuick install
Example session
$datus init --datasource snowflake
↳ gather schema · SQL history · business knowledge
✓ semantic model drafted — ready for team review
Show net revenue by region
review model → DOSI validates → plan metric query · compile warehouse-native SQL
↻ inspect definitions, SQL & lineage
· teams approve meaning and validate source data
Built on Apache Ossie (incubating)Bring your own warehouseBring your own model
Datus, at a glance

One shared context. From business knowledge to agent action.

A workspace for teams, a complete data Agent, and semantic execution grounded in an open specification. Datus brings them together around your business context.

Existing knowledge

Documents
SQL & ETL
Warehouses
Datus

Datus Studio

A shared workspace for Agent-driven data engineering.

Datus Agent

A complete data Agent for engineering and analysis.

Ontology + semantic model

DOSI Engine

Execute compatible Ossie definitions as native SQL.

Apache Ossie Spec

An open, vendor-neutral semantic modeling specification.

Put context to work

Teams
AI agents
Applications & BI

Business-aware

Connect business concepts and relationships to metrics, calculations, and source data.

Explore business meaning

Agent-native

Work with Datus Agent in Studio, or bring context and execution into your own agent workflows.

Explore Agent workflows
Business-aware

Give agents a model of your business.

Bring business concepts, relationships, and calculation rules together. Datus connects your business ontology to a reusable semantic layer, with definitions your team can review.

Connect the concepts behind your business.

Connect business concepts and relationships to your semantic definitions, so an Agent can follow what a customer, order, or transaction means.

Explore the semantic layer
Northstar business contextSelect a business concept
Customer
Mapped datasetcustomers · customer_id
Business propertiescity · margin · order_count · return_rate
Business relationshipsOrder → placed_by → Customer Membership → held_by → Customer
Agent-native

Build with context. Put it to work.

Develop data systems, create visual analysis, and answer business questions from one shared business context.

A data Agent for the work behind the answer.

Use Datus Agent in Studio to explore data, develop and debug SQL, build semantic models, and inspect results in one workspace.

Explore Datus Agent
Datus StudioCommerce workspaceD
business-rules.mdUTF-8
# Business definitions
Revenue = SUM(orders.amount).
Group by order status for comparison.
Use this definition in generated SQL.
SQL results2 rows · sample result
statusrevenue
completed350.00
cancelled100.00
Datus Studio
Datus StudioCommerce workspaceD
business-rules.mdUTF-8
# Business definitions
Revenue = SUM(orders.amount).
Group by order status for comparison.
Use this definition in generated SQL.
SQL results2 rows · sample result
statusrevenue
completed350.00
cancelled100.00
Audit-ready

Business meaning, backed by a trustworthy runtime.

Review definitions, inspect DOSI’s native SQL, and check the sources and calculations behind a report.

Northstar · recorded artifactsDuckDB
northstar_premier.yamlReview example
− Previous
name: return_handling
expression: >-
  SUM(returns.processing_cost_cents)
+ Proposed
name: return_handling
expression: >-
  SUM(returns.processing_cost_cents*0.01)

Semantic Hub · review fixture. Approve and Merge only change this preview.

How it works

Build context from the knowledge you already have.

Start with the knowledge already present in your data systems. Datus Agent helps turn it into connected models that teams can review, execute, and improve.

DocumentsBusiness rulesWarehouse schemasTables & fieldsSQL & ETLExisting logicDatus AgentBusiness rulesTables & fieldsExisting logicGather existing knowledge
1 / 5
An open foundation

Open definitions. Native execution.

Apache Ossie is an open, vendor-neutral specification for semantic models. DOSI makes compatible Ossie definitions executable as native SQL.

Keep business meaning in reviewable Ossie files. Convert supported existing models, then validate and execute them with DOSI on the data source you choose.

  1. Open specification

    Apache Ossie

    Define datasets, relationships, dimensions, and metrics in reviewable files.

  2. Compatible execution runtime

    DOSI

    Validate supported definitions, plan the request, and generate native SQL.

  3. Native SQL execution

    Your data source

    Run on the selected supported source; inspect the SQL and returned results.

Apache Ossie (incubating) is an open specification. DOSI is a compatible runtime distributed under Elastic License 2.0.

In practice

Business context for the decisions your industry makes.

Connect the definitions and relationships behind everyday decisions. These illustrative scenarios show how teams could put Datus to work.
An apparel fulfillment workspace with packed orders and a garment return being inspected.

See which sales create margin.

Connect customers, orders, returns, and fulfillment with a reviewed margin definition. Agents can investigate channel performance; teams can trace the calculation back to costs and source records.

Illustrative scenario · example question
Which channels generate margin after returns and fulfillment costs?
Explore model reuse

Put shared business context to work.

Business meaning for agents. A workflow your team can share. Execution you can inspect. Start in Studio or build with DOSI.
Get Started FreeQuickstart DOSI
FAQ

Frequently asked questions

The relationships, boundaries, and choices behind shared business context.

What does “open” mean for Datus?

Open refers to inspectable, reusable definitions based on the Apache Ossie specification and supported interfaces that work with your stack. DOSI uses Elastic License 2.0. The datus-agent project is open-source; these are different licensing models.

How do ontology and a semantic layer work together?

Ontology expresses business concepts, roles, and relationships. A semantic layer defines metrics, dimensions, calculations, and mappings to source data. Datus connects them so teams and agents can relate business meaning to the definitions behind a query.

Where does query execution happen?

DOSI turns compatible definitions into native SQL for the selected supported data source. Its adapters and interfaces determine the execution path. Reusing definitions across sources does not imply automatic cross-warehouse federation.

How can a team check an answer?

Inspect the model and its source mappings, trace lineage, review generated SQL, and validate the returned data. Supported validation and planning checks expose execution constraints; teams still review business meaning and source-data quality.

How do Studio, Datus Agent, and DOSI fit together?

Studio is the workspace for collaborative Agent-driven data work. Datus Agent is a complete data Agent for engineering and analysis. DOSI is the semantic execution module and can also be used independently through its supported interfaces.

Related resources

In the spotlight

Explore the blog