Explanation

Understanding-oriented background. Read this to deepen your mental model of Hadron, not to complete a task.

• What is Hadron — what the platform does and who it's for.
• Agents and Apps — what an Agent is, what an App is, and how the two layers fit together (the PWA analogy).
• Architecture — entity hierarchy: organizations, agents, memories, apps.
• Understanding memory — what memory is in Hadron, the different types, how it's stored and shared.
• Memory access — how agents and apps gain access to a memory, and what the different access levels mean.
• Memory ownership and lifecycle — which entity owns each memory in Hadron, and what happens when an Agent, App, or Memory is deleted.
• Subscriptions — how an organization subscribes to a memory or agent it doesn't own, and what the subscription buys.
• Edge conditions — when to use deterministic edge conditions vs. LLM-controlled routing, and the model behind the portal's condition builder.
• Assets vs. References — why uploaded files and citable sources are separate primitives, and when to reach for each.
• Authentication — Hadron's two credential paths (AppKey for App backends, UserApiKey for interactive MCP), why they exist, and which one fits which use case.
• The RAG tech stack — why Hadron's vector index uses nomic-embed-text and pgvector — the privacy posture behind the choice, and the two supported embedding-server backends (Ollama and AWS SageMaker) an operator can pick from.
• CLI vs. MCP for a coding agent — the two ways an agent reaches a Hadron server, compared on the axis that usually decides it: context-window tokens. Plus auth, structured output, and traversal.