Skip to main content
Version: 2026.1

Configuration

This section is the field-by-field reference for everything you can configure in the bundle. For the mechanism that loads and merges configuration — layers, export endpoint, reload paths — see Architecture → Configuration System. Terminology is defined in Core Concepts.

Where to go

I want to…Read
Set the bundle up in a fresh projectInstallation
Create or edit an agentAgents
Define named inference providers (byok, github, Ollama, HF, …)Inference Providers
Create a custom skillSkills
Connect an agent to MCP tool serversMCP Servers
Expose project files to an agent for readingFile Staging
Configure agent template generationAgent Templates
See the catalog of SDK toolsTool Security Reference
Tune env vars, timeouts, provider tokensEnvironment Variables
Use a strict OpenAI-compatible provider (Cerebras, Ollama, vLLM, …)Provider Compatibility
Ship preset agents or skills from my own bundleShipping Presets

The merge model at a glance

Every agent and every skill comes from one of three layers. Higher layers override lower layers by name — full-object replacement, no field-level merging.

Layer (highest wins)Who manages itWhere it lives
Studio UI editsAdministratorsSettingsStore (default) or var/config/agent/*.yaml
Container configProject codepimcore_agent.agents.definitions, auto-prepended YAML
Bundle presetsBundle authorspimcore_agent.agents.paths / skills.paths in bundles

In practice: a bundle ships sensible defaults; a project overrides any of them from code; an administrator tweaks anything further at runtime from the Studio UI without touching code. Upgrading a bundle never clobbers an administrator's edits. Every entry in the Studio UI carries a bundle or user source badge.

Full mechanics — export endpoint, reload paths, skill materialization — in Architecture → Configuration System.