Overview01
github.com/xraph/forge/extensions/ai is a Forge extension that wires core AI services into the container.
It is intentionally a thin wrapper around github.com/xraph/ai-sdk and focuses on DI registration, not a full platform bootstrap.
What It Registers Automatically02
aisdk.LLMManager(with key aliases:forge.ai.sdk.llmManager,forge.ai.llmManager)aisdk.StateStoreaisdk.VectorStore*ai.AgentFactory*ai.AgentManagerTraining interfaces only when
config.Training.Enabled == true:ai.ModelTrainerai.DataManagerai.PipelineManager
What It Does Not Auto-Register03
No automatic route mounting. You must register
AgentControllerroutes yourself.No automatic startup of inference engine, middleware, or monitoring packages.
No automatic LLM provider registration from
config.LLM.Providers(providers are currently registered manually).
Important Runtime Notes04
State store creation falls back to in-memory store when configured backend creation fails.
Vector store creation falls back to in-memory store when configured backend creation fails.
Agent definitions are held in memory by
AgentManager.Extension
Health()currently returnsniland does not aggregate component checks.
Read This Next05
Build a working setup with manual provider registration and type-based DI.
Deep feature behavior, template coverage, and current implementation limits.
Field-level config behavior, defaults, and production-safe config patterns.
Constructor graph, aliases, eager registration, and preferred Vessel pattern.
Exact routes exposed by AgentController, payloads, and behavior.
How the extension relates to the training and inference subpackages.
Grouped function-level reference for extension entry points and subpackages.
Fix common startup and DI issues quickly.