Package Exports
- @yourgpt/llm-sdk
- @yourgpt/llm-sdk/adapters
- @yourgpt/llm-sdk/anthropic
- @yourgpt/llm-sdk/azure
- @yourgpt/llm-sdk/google
- @yourgpt/llm-sdk/ollama
- @yourgpt/llm-sdk/openai
- @yourgpt/llm-sdk/openrouter
- @yourgpt/llm-sdk/xai
Readme
@yourgpt/llm-sdk
Multi-provider LLM SDK with streaming. One API, any provider.
Installation
npm install @yourgpt/llm-sdk @anthropic-ai/sdkFor other providers (OpenAI, Google, xAI), see Providers Documentation.
Quick Start
// app/api/chat/route.ts
import { streamText } from "@yourgpt/llm-sdk";
import { anthropic } from "@yourgpt/llm-sdk/anthropic";
export async function POST(req: Request) {
const { messages } = await req.json();
const result = await streamText({
model: anthropic("claude-sonnet-4-20250514"),
system: "You are a helpful assistant.",
messages,
});
return result.toTextStreamResponse();
}# .env.local
ANTHROPIC_API_KEY=sk-ant-...With Copilot SDK
Use createRuntime for full Copilot SDK integration with tools support:
// app/api/chat/route.ts
import { createRuntime } from "@yourgpt/llm-sdk";
import { createAnthropic } from "@yourgpt/llm-sdk/anthropic";
const runtime = createRuntime({
provider: createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY }),
model: "claude-sonnet-4-20250514",
systemPrompt: "You are a helpful assistant.",
});
export async function POST(req: Request) {
return runtime.stream(await req.json()).toResponse();
}Documentation
Visit copilot-sdk.yourgpt.ai for full documentation:
- All Providers - OpenAI, Anthropic, Google, xAI
- Server Setup - Runtime, streaming, tools
- Tools - Server-side and client-side tools
- LLM SDK Reference - streamText, generateText
License
MIT