omi-backend-workflow

Guides development on the Omi voice-companion backend, a FastAPI service layered as database, utils, routers and main, covering endpoint creation, the audio-to-facts conversation pipeline, LLM memory extraction, LangGraph chat routing with retrieval tools, Firestore Pinecone Redis and Cloud Storage access, local setup, and Modal or container deployment. Use when editing backend Python in a repository verified to match the Omi layout, such as adding endpoints, changing conversation or memory handling, chat tools, or data access. Not for mobile or web client work, unrelated Python services, or infrastructure provisioning beyond the two documented deployment paths.

Version

v1.0.0

Size

19 KB

Updated

2026-10-12

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.