Skip to content

Reference

Information-oriented technical descriptions — structured for lookup rather than reading end-to-end.

  • Node types — the five nodeType values (info, abstract, record, system, reference), their search behavior, and how to choose between neighbors.
  • URN composition — how Hadron URNs are built: type registry, hierarchy grammar, memory-role markers, alias categories, slug rules.
  • Mustache template syntax — variable resolution order, escaping, partials, and missing-variable behavior in node content.
  • Conversation routing — how topics, conversations, stages, edges, and goals fit together.
  • Chat API — GraphQL surface for driving a Hadron-managed chat from a third-party integration.
  • MCP tools — the h-* tools Hadron exposes through MCP, categorized by purpose.
  • hadron CLI — command surface, global flags, stable exit codes, URN rules, write semantics, and the raw-GraphQL escape hatch.
  • MCP App selection — h-list-apps and h-set-active-app: how multi-App OAuth callers pick an App per MCP session, and the typed-error vocabulary.
  • Asset upload — the bi-directional asset-upload tool: what it does, what it stores, limits, lifecycle, encryption.
  • RAG vector index — per-memory semantic retrieval: what gets embedded, when, how to search it (keyword / vector / hybrid + passages), staleness, and the encrypted-memory disclosure.
  • GraphQL API — full type, query, and mutation reference, auto-generated from the server schema.
  • Data model — entity reference with ERD diagrams, auto-generated from the Prisma schema.