OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Muxi

MUXI is an open-source, self-hosted AI application server for deploying and operating agent formations. Its infrastructure includes orchestration, memory, knowledge, tools, role-based access control, proactive behavior and observability.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Muxi — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use MUXI when you need a self-hosted server to deploy and operate complete agent formations, rather than only a framework for authoring agent logic.

Who it is for

  • Teams deploying complete AI agent systems on self-hosted infrastructure.
  • Developers building applications that need to connect to deployed formations through SDKs.
  • Operators who need integrated memory, access controls and observability for agent deployments.

Documented uses

  • Pull and deploy an agent formation with the MUXI CLI.
  • Chat with a deployed formation through the CLI.
  • Connect an application to a formation and stream chat responses using an official SDK.
  • Package agents, knowledge, memory, tools, workflows and policies into a deployable formation.
  • Operate agent systems with scoped memory, group-based access control and observability.
Before you choose

Requirements & limits

The README provides CLI installation commands for macOS, Linux and Windows and identifies the project as open source.

  • MUXI is server infrastructure; the README distinguishes it from frameworks used to write agent logic.
  • Formations are declarative deployable units that can include agents, knowledge, memory, tools, skills, workflows, triggers, policies and operational behavior.
  • The README lists official SDKs for Python, TypeScript, Go, Ruby, PHP, C#, Java, Kotlin, Swift, Dart, Rust and C++.
  • The documented quick start uses a formation ID and client key in its Python SDK example.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Stream chat from a running formation with the Python SDK

Connect a Python client to a running MUXI formation and print streamed response text.

Before you start

  • Python 3.10 or later.
  • A running MUXI server, a formation ID, and a client key.

Steps

  1. Install the Python SDK with the command below.

    Documented command
    pip install muxi-sdk

  2. Create a FormationClient with the server URL, formation ID, and client key.

  3. Call client.chat_stream({"message": "Hello!"}) and print the text value from each returned event, as shown in the SDK quick-start example.

Expected outcome

The example streams chat events and prints response text as events arrive.

Guide limitations

  • The example assumes a server at http://localhost:7890 and uses placeholder formation and client-key values; it does not document how to create or obtain them.
  • The SDK page describes supported usage but does not establish that this example has been independently tested.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
muxi-ai/muxi · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

LangChain / LangGraph — The README contrasts these Python libraries for writing agent logic with MUXI's deployment and operations infrastructure.

CrewAI — The README contrasts this Python framework with MUXI's server infrastructure for deploying and operating agent systems.

Explore project →

AutoGen — The README contrasts this multi-agent framework with MUXI's server infrastructure for deploying and operating agent systems.

Explore project →