Core domain types, schemas, and semantic conventions for LLM cost metrics

LLM eval & testing toolkit

Professional NPM package for tracking LLM API costs, managing budgets, and monitoring usage across multiple providers

Estimate token usage and cost across OpenAI, Anthropic, Gemini and more — as a library, CLI, and terminal dashboard.

[llm-ui](https://llm-ui.com) markdown block.

Unified LLM API with automatic model discovery and provider configuration

Typescript bindings for langchain

Langfuse integration for OpenAI SDK

Provider-agnostic LLM port interface, registry, cost gating, content blocks, validation strategies. The foundation of llm-ports.

Provider-neutral LLM service interface for the DeepSeek Harness

AWS SDK for JavaScript Cost And Usage Report Service Client for Node.js, Browser and React Native

One interface to hundreds of LLM models, zero dependencies, tons of features, for Browser and Node.js

Wrap your LLM client once and capture exact token counts and cost on every call — the shared foundation the other Cendor tools build on.

Graphql query cost analyzer. Use it to protect your GraphQL servers against DoS attacks, compute data consumption per user and limit it.

Type-only Branded<B> nominal-typing primitive for the DeepSeek Harness

Provider-routed LLM request retry policy for the DeepSeek Harness

Hardware accelerated language model chats on browsers

Per-test LLM API cost tracking with budgets and baseline comparison

LLM cost limiter middleware with per-user, per-key, and per-model budgets, token accounting, and hard or soft cutoffs for production API gateways.

Daily LLM token pricing data with automatic updates