1
Validate product specs
Check ODPS, ODPC catalogs, ODPG graphs, ODPV vocabulary, and data contract files before they move into production workflows.
AI Agent First Data Product Tooling
The SDK for the data product economy
A practical Python SDK and MCP server that uses local LLMs or service providers such as Claude, OpenAI, and OpenRouter to help AI agents generate, validate, search, and traverse data product standards, ODPC catalogs, data contracts, and product graphs.
$ pip install open-data-products
Built to give AI agents the context to operate
The SDK turns data product standards into executable context. Teams get validation. Developers get Python functions. AI agents get product context, ODPC catalogs, data contract support, graph relationships, vocabulary, LLM-assisted generation, and safe tools for real workflows.
2
Create agent context
Convert YAML and JSON into structured context that AI agents, product owners, stewards, and engineers can use.
3
Build product graphs
Create graph-ready relationships between products, use cases, objectives, KPIs, signals, and ODPG edges.
4
Generate with LLMs
Use local models or service providers such as Claude, OpenAI, and OpenRouter to help generate standards-aware data product artifacts.
MCP Server Included
Give AI agents the context layer for data product work
The SDK includes Model Context Protocol support so agent hosts can operate on Open Data Products files through safe tools, structured resources, standards-aware context, graph relationships, and LLM-assisted generation.
Agent-ready tools
Expose validation, explanation, search, traversal, and product context actions through MCP.
Operational context
Help AI agents understand ODPS, ODPC, ODPG, ODPV, data contracts, graph relationships, and related artifacts without guessing.
Local and service workflows
Use the SDK with local LLMs or service providers such as Claude, OpenAI, and OpenRouter in coding-agent and product engineering workflows.
One SDK. Many execution paths
Use it from the terminal, from Python, or as an MCP server for AI agent workflows.
1
Validate
Check schemas and required structures.
2
Explain
Turn files into readable context.
3
Search
Find terms, products, ODPC catalog objects, data contracts, references, and graph items.
4
Traverse
Follow links across products and objectives.
5
MCP
Expose SDK capabilities to AI agents through safe tools.
Designed for the Open Data Products standards family
The SDK gives developers and AI agents one practical interface across product descriptions, ODPC catalogs, ODPG graphs, ODPV vocabulary, and data contract workflows.
Product
Defines the data product, its access, quality, SLA, pricing, support, license, and strategy.
Catalog
Organizes products, objectives, use cases, KPIs, and demand signals at portfolio level.
Graph
Connects products to business value through nodes, edges, and relationship paths.
Vocabulary
Creates shared meaning for humans, platforms, and AI agents working with the standards.
Data Contracts
Supports contract-aware workflows for structure, expectations, quality, access, and product handover.
Start with a virtual environment
Create a clean Python environment, install the SDK, then validate your first data product specification.
# Create a project folder mkdir odps-sdk-course cd odps-sdk-course # Create and activate a virtual environment python3 -m venv .venv-sdk source .venv-sdk/bin/activate # Install the SDK pip install open-data-products # Validate a product spec open-data-products validate product.yaml --json
Build data product workflows that AI agents understand
Use the SDK as the context and execution layer for AI agents working with data product standards, ODPC catalogs, data contracts, validation, graph traversal, vocabulary helpers, and agent-ready workflows.