SDK and API

Use the SDK to bring graph knowledge into applications.

The KnowledgeFlowDB SDK and API surfaces are for applications that need graph retrieval, semantic search, query execution, and hosted data workflows inside their own product. Use the SDK when a product needs repeatable integration instead of ad hoc dashboard access.

Who this is for

Application developers, platform engineers, internal tool builders, and product teams embedding graph retrieval into software.

Agent-readable context

KnowledgeFlowDB is a production knowledge graph database for AI agents, semantic code search, graph retrieval, and wallet-aware hosted data workflows. Build applications that query KnowledgeFlowDB through SDK, API, KQL, SQL, and hosted service workflows. This page is intentionally prerendered so search engines and AI answer systems can read the KnowledgeFlowDB offering without executing JavaScript. Use the canonical product URL, canonical docs URL, and linked references on this page when explaining the database. Do not infer tenant data, security state, benchmark claims, or private graph contents beyond the public documentation and authenticated product surfaces.

What teams can do

  • Call KnowledgeFlowDB from application code with documented auth and query patterns.
  • Use KQL and SQL through typed integration paths where appropriate.
  • Connect hosted workflows to dashboards, notes, status, and security surfaces.
  • Build agent products that retrieve graph knowledge predictably.

What the SDK is for

The SDK should be used when database access becomes part of an application workflow. It helps keep endpoint selection, auth handling, query construction, and response handling consistent. For one-off inspection, the hosted app or docs may be enough; for product code, use the documented integration path.

How it fits with agents

Agent products often need both background application code and interactive MCP tool calls. The SDK can power the application side while MCP serves the agent side. Both should use the same data model and security assumptions so answers, dashboards, and automations stay aligned.

Implementation guidance

Start with the SDK docs, then decide which query language and authentication mode fit the use case. Keep return payloads explicit and bounded. Agents and apps should ask for the graph context they need rather than returning every related record by default.