Providers

llamacpp

llama.cpp server — run GGUF models on CPU or GPU with minimal overhead.

import { llamacpp } from '@agentskit/adapters'

const adapter = llamacpp({
  url: 'http://localhost:8080',
})

Options

Option	Type	Default
`url`	`string`	`http://localhost:8080`
`fetch`	`typeof fetch`	global

vllm

vLLM — high-throughput self-hosted inference with OpenAI-compatible API. For production workloads on your own GPUs.

openaiEmbedder

OpenAI text embeddings — text-embedding-3-small / -large. Default choice for most RAG stacks.