Core configuration management library (Rust crate - use via cargo or build from source)
Detox driver for Wix Pilot usage
General-purpose agent with transport abstraction, state management, and attachment support
HTTP daemon and CLI for agent-driven browser extension testing with Playwright
Stringify your JSON at max speed
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
A library for working with LLMs in Grafana plugins
zlib port to javascript - fast, modularized, with browser support
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
Reads / writes floats / doubles from / to buffers in both modern and ancient browsers.
Lightweight, zero-dependency LLM API cost & token usage tracker for OpenAI, Anthropic, Gemini, Mistral, Groq, and DeepSeek
Typescript bindings for langchain
Faster swc nodejs binding
## Table of Contents
Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c
Display language model outputs in your React project.
[llm-ui](https://llm-ui.com) markdown block.
Model Context Protocol implementation for TypeScript
Hardware accelerated language model chats on browsers
[llm-ui](https://llm-ui.com) code block.
ESLint rules that catch the patterns LLM agents get wrong — and teach them to self-correct
LLM eval & testing toolkit
AI-powered knowledge graph platform with WebGL visualization
Agentics CLI - Pure orchestration layer for agentics platform services