The Open-source AI Application Server

​

---

No one builds their own Nginx to deploy a website. No one should reinvent infrastructure to build AI.

---

Deploy Intelligence

MUXI (/ˈmʌk.siː/) is production infrastructure for AI agents. Not a framework. Not a wrapper. A server – where agents are native primitives with built-in orchestration, memory, observability, and scale.

Concept	Docker	MUXI
Engine	Docker Engine	Server + Runtime
Definition	Dockerfile	Formation
Registry	Docker Hub	MUXI Registry
CLI	docker	muxi

Note

MUXI introduced the Agent Formation Standard – an open spec for declarative AI systems. Agents, knowledge, A2A, and MCP tools defined in portable .afs files.

Demo

Quick Start

Install:

brew install muxi-ai/tap/muxi                        # macOS
curl -fsSL https://muxi.org/install | sudo bash      # Linux
powershell -c "irm https://muxi.org/install | iex"   # Windows

Run:

muxi pull @muxi/hello-muxi   # pull a formation
muxi deploy                   # deploy it
muxi chat hello-muxi         # talk to it

Three commands. Your agent is running, stateful, and accessible via API.

📚 Docs: Quickstart | Installation

---

Build on Top with SDKs

from muxi import FormationClient

client = FormationClient(
    server_url="http://localhost:7890",
    formation_id="hello-muxi"
)

for chunk in client.chat_stream({ "message": "Hello!", "user_id": "user_123" }):
    print(chunk.get("text", ""), end="")

SDKs available for Python, TypeScript, Go, and 9 more languages.

📚 Docs: SDKs | API Reference

---

How MUXI Compares

	MUXI	LangChain / LangGraph	CrewAI	AutoGen
What it is	Server infrastructure	Python libraries	Python framework	Multi-agent framework
Deploy	muxi deploy	Write your own	Write your own	Write your own
Configure	Declarative .afs files	Imperative code	Imperative code	Imperative code
Multi-tenancy	Built-in isolation	Build it yourself	Not supported	Not supported
Memory	Three-tier (buffer + persistent + vector)	Bring your own	Short-term only	Bring your own
Tools	1,000+ via MCP, loaded once	Per-call schema injection	Per-call injection	Per-call injection
Observability	349 event types, 10+ export targets	LangSmith (paid)	CrewAI+ (paid)	Limited
LLM Providers	21 providers, 300+ models	Multiple	Multiple	Multiple

Key numbers: <100ms avg response • 80%+ test coverage • 92% semantic cache hit rate

---

Features

• Declarative agents – .afs files, version-controlled, auto-discovered. Docs
• Three-tier memory – buffer, persistent, and semantic memory built in. Docs
• 1,000+ MCP tools – GitHub, Slack, Stripe, databases, and more. Docs
• Multi-tenant – per-user isolation, RBAC, OAuth. Docs
• Observability – 349 event types, real-time streaming, 10+ export targets. Docs
• Intelligent orchestration – Overlord routes to specialists, decomposes tasks. Docs
• Async processing – triggers, webhooks, scheduled tasks. Docs
• Any LLM – 21 providers, 300+ models, no lock-in. Docs

---

Example Formation

# formation.afs -- define your AI system (it's just YAML)
schema: "1.0.0"
id: "customer-support"
description: Helps customers with product support and refunds

llm:
  models:
    - text: "openai/gpt-4o"
  api_keys:
    openai: "${{ secrets.OPENAI_API_KEY }}"

agents: []  # auto-discovered from agents/*.afs

# agents/sales-assistant.afs -- define an agent
schema: "1.0.0"
id: sales-assistant
name: Sales Assistant
description: Helps customers with product questions

system_message: Help customers find products and answer questions.

knowledge:
  sources:
    - path: knowledge/product-info.docx
    - path: knowledge/shipping-rates.csv

muxi deploy   # that's it -- running, stateful, API-accessible

📚 Docs: Formation Schema | Examples

---

Who Is MUXI For?

• Platform builders – Building a SaaS with AI features? MUXI handles orchestration, memory, and multi-tenancy so you can focus on your product.

• Internal tool builders – Deploying AI assistants for your team? MUXI gives you SOPs, observability, and enterprise-grade infrastructure out of the box.

• Developers tired of framework hell – Spent months on LangChain orchestration code? MUXI replaces it with YAML configuration and a single deploy command.

Open Source & Self-Hosted

MUXI is open-source and self-hostable. Your data stays on your infrastructure. No vendor lock-in. No per-seat pricing. No usage limits.

• Self-hostable – run anywhere, owned by you
• Observable – see what's happening, always
• Declarative – version-controlled and reproducible
• Open – no lock-in, no surprises

---

Documentation

Looking for...	Go to
Getting started	Quickstart →
SDKs (12 languages)	SDKs →
How MUXI works	ARCHITECTURE.md
Contributing	CONTRIBUTING.md
All repositories	REPOSITORIES.md
Licensing	LICENSE.md
Roadmap	Roadmap →

---

Agent Skills

This repo includes an Agent Skill that gives any compatible AI agent (Claude Code, Cursor, GitHub Copilot, VS Code, etc.) deep knowledge of the MUXI platform.

See skills/ for setup instructions.

---

Get Involved

• Star this repo to follow progress
• Discussions – ask questions, share ideas, get help
• Roadmap – see what's coming
• @muxi_ai – follow for updates
• CONTRIBUTING.md – contribute code

---

Who's Behind This

MUXI is created by Ran Aroussi, author of Production-Grade Agentic AI (665 pages) and an open-source developer whose tools are used by millions of developers daily.

Important

MUXI is built on the principles from Production-Grade Agentic AI – a comprehensive guide to building enterprise AI agent systems in production. Download the PDF version here ›.

---

License

Server and Runtime are ELv2. Everything else (CLI, SDKs, formations, schemas) is Apache 2.0.

TL;DR: Use MUXI freely for your products and business. The only restriction: don't resell MUXI itself as a hosted service. See LICENSE.md for details.

---

GitHub • Twitter • Discussions

_{For AI/LLM agents: muxi.org/llms.txt}