Concepts
Postgram is a self-hosted private knowledge store for humans and agents. It keeps knowledge in typed entities and layers retrieval, graph context, and background processing on top of the same data model.
What this page covers
Section titled “What this page covers”This page summarizes how Postgram is organized, what it stores, and what makes it useful for both humans and automation.
Core workflow
Section titled “Core workflow”- Ingest content as typed entities (
memory,person,project,task,interaction,document). - Let Postgram enrich content in the background (chunking, embedding, optional extraction).
- Query with hybrid search to retrieve ranked results, including optional graph context.
- Use explicit or extracted relationships to navigate connected context.
- Postgram is designed for private use by an individual or small team, not as a public multi-tenant SaaS platform.
- Every public API is surfaced through REST, MCP, and CLI using the same core entity types.
- For implementation details of each concept, see: Entity Model, Memory Roles, Hybrid Search, and Knowledge Graph.