Test your LLM-powered apps with a TypeScript-native, Vitest-based eval runner. No API key required.

Model Context Protocol implementation for TypeScript

Provider-neutral LLM service interface for the DeepSeek Harness

TypeScript SDK for Laminar AI

Provider-routed LLM request retry policy for the DeepSeek Harness

Typescript bindings for langchain

pi-ai-backed DeepSeek adapter for the DeepSeek Harness LLM seam (design-verification twin of dsh-llm-deepseek)

Show the instruction graph your coding agents actually receive.

Display language model outputs in your React project.

Client library to connect to the LangSmith Observability and Evaluation Platform.

First-message LLM provider plugin for DeepSeek Harness session titles

Additive request-field registry for the official DeepSeek LLM API adapter

A NodeJS RAG framework to easily work with LLMs and custom datasets

LLM eval & testing toolkit

DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam

Debugger frontend for React Native based on Chrome DevTools

Hardware accelerated language model chats on browsers

Dedicated types library for ramda

micromark extension to support math (`$C_L$`, `\(C_L\)`)

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