Search

Calculate LLM token costs from litellm pricing data

Pack the most important text into a fixed LLM context-window token budget.

Identifiers designed to survive being read, copied and re-emitted by language models

Interfaze LangChain integration for TypeScript/JavaScript

Superagent safety agent tool for Vercel AI SDK

Magic Hour tools for LangChain.js — AI video (Sora 2, Veo 3.1, Kling 3.0, Seedance, WAN 2.2) and image generation as LangChain tools.

Oxe - a terminal-based AI coding agent (native TypeScript CLI).

HumanLayer's vendored OpenAI provider for Effect AI SDK

HumanLayer's vendored OpenAI-compatible provider for Effect AI SDK

ZUI UI for AI-assisted enterprise apps: assistant dock, thread, streaming markdown, tool calls, approvals, diff review, structured output, citations, provider adapters

OpenCode AI SDK provider for the ZMLLMGW model gateway

TypeScript SDK for the TypeSafe API

An OpenRouter provider integration for Effect AI SDK

OptiVision RAG: extreme token compression for vision-language document retrieval (npx launcher for the Python CLI)

Official client SDK and prompt utilities for GPT images 2.5 - Free AI Image Generator & Editor Online (https://images25.art)

Benchmark Apple Silicon memory bandwidth, disk speed, and MLX model inference performance to find the optimal LLM size

SWC plugin for transforming Workflow SDK code

n8n nodes for LLM chat via OpenAI-compatible Chat Completions API (llama-server, Ollama /v1, vLLM, etc.)

Temporary package placeholder for staged publishing

Temporary package placeholder for staged publishing