chatoyant
Unified TypeScript SDK for LLM providers (OpenAI, Anthropic, xAI) with streaming, structured outputs, and zero dependencies.
What if your AI library just... worked?
You wanted to add AI to your app, not adopt a small child. Yet here you are, nursing 47 transitive dependencies, debugging some guy's questionable abstraction choices, and wondering why a simple chat completion needs a PhD in framework archaeology. The "AI SDK" space has become a bloatware arms race where everyone's competing to wrap the most layers around a fetch call.
Chatoyant says "nah" to all that. Zero dependencies. One unified API. OpenAI, Anthropic, xAI — all speak the same language now. You get streaming, structured outputs, tool calling, and full TypeScript inference without importing half of npm. It's just fetch calls with really good types. Ship your AI feature this afternoon, not next quarter.
Current State
Stage: Empathy
Discovering and understanding deeply the pain points of your niche market.
Category: Library
Some functionality implemented in ready-to-use code form, available as open source software on github. Ideally in Rust for maximum reuse across tech stacks.
Users
not tracked yet.
Revenue
not tracked yet.