{"library":"node-llama-cpp","type":"library","category":null,"description":"Run large language models (LLMs) locally from Node.js using llama.cpp bindings. Version 3.18.1 provides pre-built binaries for macOS, Linux, and Windows (Metal, CUDA, Vulkan) with automatic fallback to source build via cmake (no node-gyp or Python required). Supports JSON schema enforcement, function calling, embedding, reranking, and chat sessions. Full TypeScript types included. Active development with frequent releases synced to upstream llama.cpp. Key differentiator: zero-config GPU acceleration and safe token injection prevention.","language":"javascript","status":"active","version":"3.18.1","tags":["javascript","llama","llama-cpp","llama.cpp","bindings","ai","cmake","cmake-js","prebuilt-binaries","typescript"],"last_verified":"Sun Jun 07","install":[{"cmd":"npm install node-llama-cpp","imports":["import { getLlama } from 'node-llama-cpp'","import { LlamaChatSession } from 'node-llama-cpp'","import { getLlama } from 'node-llama-cpp'"]},{"cmd":"yarn add node-llama-cpp","imports":[]},{"cmd":"pnpm add node-llama-cpp","imports":[]}],"homepage":"https://node-llama-cpp.withcat.ai","github":"https://github.com/withcatai/node-llama-cpp","docs":null,"changelog":null,"pypi":null,"npm":"node-llama-cpp","openapi_spec":null,"status_page":null,"smithery":null,"compatibility":null}