3 projects
oq-ai-usage
Per-user/per-tenant AI token and cost usage recording and analytics. No hard dependencies; framework-agnostic core.
oq-ai-ocr
Document ingestion and OCR: byte-level format detection, text-layer-first reading, local PP-OCR engines, an escalation policy, and the eval harness that settles all of it with evidence.
oq-ai-router
Provider-agnostic LLM routing: free-first fallback chains, host-supplied policy, per-tenant keys. Transport by LiteLLM.