Skip to content

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

2.4 KB
Raw Blame

Choose a deployment path

If someone has already provided a service URL and API key, go directly to CLI setup or agent integration. The paths below are for people deploying and operating the service.

Goal Reading order Completion check
Try it locally Quick start Import a document, retrieve a match and read its content
Host a shared service Self-host a server → Authentication → Public access Verify persistence, authorized access, unauthorized rejection and initial data processing
Install an enterprise delivery Pre-deployment checklist → Install and verify → Upgrade and troubleshoot Verify each item in the delivery manifest and installation guide

Enterprise deployment depends on delivery artifacts, images and environment requirements; check the manifest first.

Configure models and access

For initial model setup, use Configure models and services. For a field lookup, use server configuration fields. The server's ov.conf and the client's ovcli.conf have different responsibilities; see client configuration for client fields.

Configure authentication and reverse proxies before exposing remote access. For MCP clients that require OAuth, continue to OAuth 2.1. For shared installations, understand multi-tenant identity and ACL inheritance. If you need encryption at rest, follow the encryption guide.

Check the running service

Choose a tool through the observability and diagnostics guide. Inspect individual requests with operation telemetry, trends with Prometheus / Grafana, and metric meanings in metric definitions. See the FAQ for common problems.

Add multi-write storage, RAGFS caching or cuVS when needed. These are optional configurations rather than prerequisites for a first deployment.