pi extension that registers your llama.cpp server as a provider and auto-discovers every model it exposes at /v1/models — context size, vision and thinking support included

llama.cpp LLM Provider

Core SDK for RunAnywhere React Native - includes RACommons bindings, native bridges, and public API

Load node modules according to tsconfig paths, in run-time or via API.

Provides a way to make requests

Cross platform child_process#spawn and child_process#spawnSync

Build tool and bindings loader for node-gyp that supports prebuilds

Ignore is a manager and filter for .gitignore rules, the one used by eslint, gitbook and many others.

TypeScript execution environment and REPL for node.js, with source map support

Determines if an object can be used as an array

Info about node `exports` field support: version ranges, categories, etc.

PostgreSQL client - pure javascript & libpq with the same API

ECMAScript JS AST traversal functions

Node.js releases data

[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/

Vite as Node.js runtime

better fetch for Node.js. Works on any JavaScript runtime!

Like which(1) unix command. Find the first instance of an executable in the PATH.

A Babel preset that enables parsing of proposals supported by the current Node.js version.

Native on-device SLM bindings (llama.cpp / GGUF). Implements SlmRuntime without an HTTP sidecar.