PostgreSQL-backed applications
For PostgreSQL-backed applications, pgCortrix is the path for bringing semantic storage closer to existing PostgreSQL infrastructure.
Other data stacks
For other data stacks, keep the operational database in place and use Cortrix to manage source-linked semantic records, retrieval evidence, and agent-facing context.
Move one workflow at a time
Start with a repository, docs folder, or internal agent workflow where ingestion, retrieval, memory, and audit are already creating repeated integration work.
Migration checklist
Use this page as an evaluation map for reducing glue code while keeping existing databases, tools, and agent frameworks in place.
Inventory
List ingestion, chunking, search, reranking, memory, and traceability components that currently require custom glue code.
Connect
Choose the access path that fits the workflow: REST, Python SDK, MCP server, framework toolkit, or pgCortrix for PostgreSQL-backed applications.
Measure
Compare maintenance cost and retrieval quality through explicit methodology, artifacts, and reproducible run manifests.