FastAPI backend with clean architecture; engine with graph-based execution; ingestion pipeline; observability stack.
Layers
- Ada Backend (
ada_backend/): repositories, services, routers, GraphQL - Engine (
engine/): agents, graph runner, LLM services, tracing - Data Ingestion (
data_ingestion/): document processing and embeddings
Data & Storage
- PostgreSQL, Qdrant, Redis, SeaweedFS
- Separate trace database for OpenTelemetry
Quick Start tutorial
Ready to build production AI?
Start with the Quick Start guide or explore the API. Join the community and help shape the open-source platform for AI agents.