HN Showcase
Back to browse
AI compatibility without compromises

AI compatibility without compromises

by Nedomas·Apr 16, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSlickBig Brain

In-process translation beats LiteLLM's proxy approach with zero extra hop.

Strengths
  • •Wire-level SDK translation preserves streaming, token counting, and all methods
  • •Six storage adapters including Prisma, in-memory, and provider-managed state
  • •Battle-tested: 1.6M threads and 22M messages in production
Weaknesses
  • •AI provider abstraction is crowded (LiteLLM, Portkey, LangChain already exist)
  • •Anthropic and OpenAI only for now; Google and Azure adapters still coming
Target Audience

AI application developers building provider-agnostic systems

Similar To

LiteLLM · Portkey · LangChain

Post Description

Built a library to translate between OpenAI Responses/Assistants APIs and other provider APIs. Provides full compatibility so it’s a total drop-in regardless of which provider you use or which features (computer use, web search).

End goal will be translating between any SDK and any other SDK with full features, no proxies, no latency.

Similar Projects