Choose Your GroundX Path

Pick the path that matches what you’re trying to do. Each path leads to its own guide — this page just routes you there.

Use Agent Harness

Use this when you want an agent — Claude, Codex, or another agent runtime — to plan and execute GroundX work for you: ingest documents, check status, search, extract structured data, debug a stuck process, or explain a GroundX concept with GroundX-specific instructions instead of guesswork.

See What Is GroundX Agent Harness? for an overview, then Install GroundX Agent Harness for per-client installation steps.

After installing, whether you connect hosted MCP (which is prod-only today) or fall back to direct SDK/REST depends on three factors: whether your client supports remote MCP/connectors, whether the MCP connection is available and connected, and whether MCP’s tool surface covers the operation you need. See Connect Hosted MCP Tools for setup or SDK/REST Fallback for the full breakdown.

Use SDKs Or REST

Use this when you’re building application code that calls GroundX directly — your own service or backend, not an agent.

Start with the Direct SDK/API Quickstart, then see the GroundX SDKs page for language-specific SDK installation.

Extract JSON From Documents

Use this when you want a document to come back as structured JSON your application can use directly. You can do this through either Agent Harness or direct SDK/REST — pick whichever fits how you want to do the work.

See Extract Data from Documents for the direct SDK path, or Extract Data With an Agent if you’d rather have an agent draft and iterate the extraction schema for you.

Deploy GroundX On-Prem

Use this when you’re planning a self-hosted or air-gapped GroundX deployment, including an ingest-only mode (mode: ingest) that runs the ingest pipeline without the retrieval/search stack.

See the GroundX On-Prem section, including GroundX On-Prem on AWS and GroundX On-Prem on OpenShift.