The official Node.js/TypeScript SDK for [Metorial](https://metorial.com) - Connect your AI agents to any MCP server with a single line of code. Deploy tools like Slack, GitHub, SAP, and hundreds more without managing infrastructure.

Bundled LLM tokenizer vocabularies (tokenizer.json set) for @plurnk/plurnk-mimetypes' tokenizer seam — exact token counting for window math.

One OpenAI-compatible endpoint for 15+ free LLM providers. Smart routing, failover, encrypted keys. Run with npx freellm.

Resolve agent.model strings to a lazy-loaded ProviderAdapter (Section 17)

Voyage AI embedding provider for Chroma

Enable usage of Mistral models with embedjs

Ecologits.js Calculator for the MistralAI API

CLI coding agent powered by Google Gemini

CLI for audio and video transcription

Simple text embeddings library

Use Mistral AI with strong typing and formatters for JSON, XML, Markdown, and SQL

Drop-in observability wrapper for OpenAI, Anthropic, Gemini, Mistral SDK clients. One-line wrap() = cost / latency / quality records.

Kinetically Orchestrated Neural Execution Engine for Code

Prompt Judy LLM Proxy Adapter for Mistral

Convert provider OCR responses into openparser@1 documents

OpenCode plugin that converts raw tool-call markup from local Ollama models into standard OpenAI tool_calls, plus line-ending normalization for file edits.

Mistral tokenizer families for tokkit.

Mistral provider for @effect-uai/core: chat-completions plus Voxtral speech-to-text and text-to-speech.

Backend provider adapters for AI Matey - Universal AI Adapter System

Enable usage of Mistral models with embedjs