Universal AI adapter - One API for 15 providers (Ollama, Cerebras, OpenRouter, Qwen, Kimi, Mistral, Perplexity, Minimax, Z AI, OpenAI, Anthropic, Groq, DeepSeek, Gemini) with Compare All, fallback, streaming

Mistral CLI

ZypeCode — A terminal-native coding assistant powered by free AI APIs

TuringPulse SDK integration for Mistral AI (TypeScript)

Mistral AI provider for Hivekeep — chat models (with tool calling, vision, streaming) AND Voxtral speech-to-text, via api.mistral.ai.

n8n node for Mistral OCR API integration with structured annotations

Unified LLM API with automatic model discovery and provider configuration

Automatic reasoning level management for pi.dev - sets the thinking level based on the selected model with sensible defaults and full customization

Mistral OCR + deterministic AST chunker for RAG pipelines

Cut your LLM bill: drop-in proxy that compresses input, output, and cache. Any provider, answers unchanged.

Ollama

MCP server to read, edit, compile, and commit LaTeX in a git-hosted project (Overleaf, GitHub, any git remote).

Claude Code skill pack for Mistral AI - 24 skills covering LLM API integration with chat, embeddings, and function calling

MemberJunction Wrapper for OpenRouter AI inference services

An MCP server for advanced AI workflow planning, sequential thinking, and task management

source-available professional agent that learns your business — connect any API, remember everything, run while you sleep

A universal, easy-to-use AI client with unified interface for OpenAI, Claude, Gemini, and Groq.

Node-RED nodes for the Mistral AI API: chat (text + vision + streaming), embeddings, and OCR.

TypeScript utilities for building LibreChat agent workflows. The package provides graph orchestration, streaming event handling, tool execution, provider adapters, and message formatting for single-agent and multi-agent runs.

Converse MCP Server - Converse with other LLMs with chat and consensus tools