Home - Open Semantic Interchange

The Universal Standard for
Semantic Data

The Open Semantic Interchange is an industry-wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for semantic data.

AI Ready Semantic Context

Write Once, Query Anywhere.

Stop redefining "Revenue" in every dashboard. OSI uses a declarative YAML standard to define metrics, dimensions, and joins — so every tool and agent in your stack works from the same source of truth.

✓

Consistent Definitions

Ensure Marketing, Finance, and Sales all see the same numbers — no more metric drift.
✓

AI-Ready Context

Give LLMs the semantic context they need to answer business questions accurately.
✓

No Lock-In

Move your business logic between platforms freely. Your metrics belong to you.

semantic_model:
  - name: ecommerce_analytics
    description: 
    ai_context:
      instructions: 

    datasets:
      - name: orders
        source: sales.public.orders
        primary_key: [order_id]
        fields:
          - name: order_date
            dimension:
              is_time: true

    metrics:
      - name: total_revenue
        expression:
          dialects:
            - dialect: ANSI_SQL
              expression: SUM(orders.amount)

About OSI

The Open Semantic Interchange (OSI) is a collaborative, open-source effort dedicated to standardizing and streamlining semantic model definitions across the data analytics, AI, and BI ecosystem.

Interoperability

Seamlessly exchange semantic models between AI agents, BI platforms, and analytics tools.

Consistency

Maintain consistent data definitions and values across every platform in your ecosystem.

Vendor-Agnostic

A common standard that works across all vendors, eliminating tool-specific inconsistencies and lock-in.

Efficiency

Reduce engineering debt and accelerate innovation by using a unified, governed semantic foundation.

The Challenge Semantic Fragmentation

×
Metric Drift Inconsistent KPIs across different dashboards.
×
Manual Translation Costly, error-prone reconciliation efforts.
×
Hallucinations Unreliable AI grounding from conflicting data logic.
×
Integration Debt Complex N-to-N custom integrations between proprietary tools.

The Solution A Unified Standard

✓
Single Source of Truth Unified semantic and metric definitions.
✓
Native Interoperability Direct exchange between platforms and AI agents.
✓
Trusted AI Grounding Agents reasoning accurately based on business logic.
✓
Reduced TCO Lower costs through automated model exchange.

Core Classes

The OSI specification defines these building blocks:

Semantic Model

Top-level container representing a complete model with datasets, relationships, and metrics.

Datasets

Logical business entities — fact and dimension tables with fields and structure.

Fields

Row-level attributes for grouping, filtering, and metric expressions.

Metrics

Aggregate calculations — sums, averages, ratios — spanning multiple datasets.

Dimensions

Categorical attributes: Where, When, Who.

Relationships

Foreign key constraints connecting datasets, supporting simple and composite keys.

Working Group Members

Leading organizations collaborating to build the future of semantic interchange

Alation

Ataccama

Anomalo

Atlan

AtScale

Bigeye

BlackRock

Blue Yonder

CARTO

Cloudera

Coalesce

Collate

Collibra

Cogniti

Count

Credible

Cube

Dataiku

Databricks

DataHub

Denodo

dbt Labs

Dremio

Domo

Elementum AI

Entropy Data

Firebolt

GoodData

Hex

Honeydew

Informatica

Instacart

JetBrains

Lightdash

Metabase

Mistral AI

Omni

Oracle

Preset

Qlik

RelationalAI

Salesforce

Select Star

ServiceNow

Sigma

Snowflake

Starburst Data

Strategy

Sundial

ThoughtSpot

Zeta Global

Working Groups

The initiative is organized into focused groups, each tackling a specific area of the specification.

Advanced Metrics & Expression Language

Complex metric calculations and a portable expression syntax

Composability

Enabling semantic models to reference and extend one another

Catalog Integration

Bridging OSI models with data catalog and governance platforms

Ontology Representation

Mapping OSI concepts to formal ontology standards

Model Converters & Developer Tools

Tooling for importing, exporting, and validating OSI models

Latest Updates

News and announcements from the OSI community

June 4, 2026

The FSI Semantic Working Group Is Live

The Financial Services Semantic Working Group has held its first formal meeting, bringing together practitioners from across banking, insurance, asset management, and market infrastructure to solve the industry's semantic alignment challenge.

The Universal Standard for Semantic Data