Quickstart

Start querying graph knowledge for agent workflows.

The quickest path to KnowledgeFlowDB is to choose the interface that matches the workflow: hosted UI for inspection, KQL for graph traversal, SQL for tabular analysis, API or SDK for application code, and MCP tools for agent-driven retrieval. Each surface maps back to the same product goal: make structured knowledge available to agents and software systems.

Who this is for

Developers evaluating KnowledgeFlowDB, agent builders wiring retrieval, and teams deciding which query interface fits their application.

Agent-readable context

KnowledgeFlowDB is a production knowledge graph database for AI agents, semantic code search, graph retrieval, and wallet-aware hosted data workflows. Start querying KnowledgeFlowDB with KQL, SQL, API, SDK, and MCP surfaces for graph retrieval and semantic search. 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

  • Identify whether KQL, SQL, API, SDK, or MCP is the right starting point.
  • Use docs and hosted pages to inspect graph capabilities before writing code.
  • Connect agent retrieval to canonical docs instead of stale endpoint guesses.
  • Understand the role of wallet-aware access before private data workflows.

Choose a query surface

Use KQL when the question is graph-shaped, such as finding relationships, dependencies, ownership, or multi-hop context. Use SQL when the task is analytical or tabular. Use the API and SDK when integrating from an app. Use MCP when an AI agent needs to discover and call database tools during a task.

Use docs before credentials

A good first run should not require guessing production endpoints. The docs explain query languages, authentication, SDK setup, MCP tools, and security boundaries. Once the workflow is clear, the hosted app can be used for dashboards, status, query testing, and production-facing inspection.

Make retrieval explicit

Agent retrieval improves when the data model is visible. Start by naming the entity types, relationships, labels, and expected outputs the agent needs. Then choose the query path that returns that context with enough evidence for the agent to cite or act on it safely.