Žiga Vaupot's Blog

OPAF Chat and Oracle Analytics Cloud via MCP From Standalone Assistant to Analytics-Aware Agent I've covered this ground before, in two earlier post series: Unlocking Oracle Analytics Cloud with AI: MCP for Oracle Analytics . This is where I introduced the MCP Server for Oracle Analytics Cloud , and how it lets general-purpose AI assistants like Claude query governed OAC data through a standard, secure protocol. Oracle Analytics Meet AI series , which expands on that theme and focuses more on the tools available from within OAC itself. This time I want to close the loop on something I left open: what happens when the AI assistant isn't a desktop client like Claude Desktop, but a private, self-hosted agent platform running entirely inside your own environment? That's the space Oracle AI Database Private Agent Factory (OPAF) occupies. It's Oracle's private agent platform, deployed and backed by your own database, on-pr...

I recently deployed Oracle AI Database Private Agent Factory (OPAF) v26.4.0 on OCI as part of my internal demo and prototyping environment. The goal was straightforward: stand up a Knowledge Agent that could ingest documents and answer questions using OCI GenAI. What I got instead was a frustrating series of database deadlocks that took most of a day to fully resolve. Here is the full story — including every dead end — so you do not have to repeat it. The Setup OPAF runs as a Podman container on an OCI compute VM in the Frankfurt region. My initial database choice was an Autonomous Database 26ai Free tier instance, which seemed reasonable for a demo environment. OPAF version: 26.4.0.0.0 Container: oracle-applied-ai-label / Podman VM: agentfactoryvm3, OCI Frankfurt Database initial: AutonomousDB23ai — ADB 26ai, Free tier LLM: OCI GenAI, meta.llama-3.3-70b-instruct, eu-fran...