Skip to main content

Overview

MeshAgent is an end to end platform for building, deploying, and hosting AI Agents. MeshAgent integrates AI Agents and human teams in real time by bundling LLM orchestration, tool integration, real-time messaging, observability, and deployment so you can ship and share agents in minutes instead of weeks.

In this guide you will learn how to:

  1. Create a MeshAgent account and project in MeshAgent Studio
  2. Install MeshAgent for Python
  3. Connect to your first MeshAgent Room and call a chat and voice agent into your room

Prerequisites

Before you start, make sure your machine matches the appropriate requirements. If you’ve never set up Python, pip, or uv before, follow the Machine Setup Guide first, then return here.

Key Concepts

  • Projects: Groups related Rooms and the Agents that serve them. It is best to create a different Project for each use case.
  • Rooms: A dedicated space for humans and Agents to collaborate in real time.
  • Agents: ChatBots, VoiceBots, TaskRunners, and Workers that you build and deploy with custom tools or out of the box MeshAgent tools. Once deployed, Agents are automatically available as a project service (available in all rooms in the project) or a room service (available only in the room they’re deployed to).

Setup Guide

Step 1: Create an account and project:

  1. In a browser, go to meshagent.com. Sign up or sign into MeshAgent Studio.
  2. Create a new project from MeshAgent Studio or using the MeshAgent CLI meshagent project create my-new-project
  3. Ensure your project has credits to start a room. Go to the Billing page to check your credits in the project. All new accounts start with $5.

Step 2: Install MeshAgent (Python)

From your terminal create or activate a virtual environment, for help with this see our Machine Setup Guide. Once your virtual environment is activated, install MeshAgent using the Python package manager of your choice.
uv add 'meshagent[all]' 
Note: Installing the entire MeshAgent SDK as shown above automatically installs the MeshAgent CLI package, but the CLI can also be installed independently using uv add "meshagent[cli]" or pip install "meshagent[cli]".

Step 3: Use the MeshAgent CLI to Connect to a Project

Authenticate and activate a project.
# A browser window will open for OAuth.
# Next the terminal will ask you to select or create a project.
meshagent setup
Optional: Alternatively, instead of running the meshagent setup command you can run:
# A browser window will open for OAuth 
meshagent auth login
meshagent project activate -i # Select a project to activate
# create an api key if necessary. The key value will be displayed only once.
meshagent api-key create --activate my-api-key
You are now authenticated and ready to use the CLI to perform operations involving a Room.

Step 4: Call an agent into a Room using the MeshAgent CLI

Let’s call a chatbot and voicebot into a new room and talk to them in MeshAgent Studio.
# Start a chat agent in the room "gettingstarted"
meshagent chatbot join --room gettingstarted --agent-name chatagent 

# Start a voicebot in the same room
meshagent voicebot join --room gettingstarted --agent-name voiceagent
Now open studio.meshagent.com and join the gettingstarted session. In the participants tab you will see the chatagent and voiceagent appear. To talk to the agent, just select it from the participants list and begin chatting! These agents will be available in the Room while you’re running them from the CLI. If you want the agents to persist in the room you will need to deploy them as a project or room service.
Tip: Mute your mic after speaking to avoid background noise triggering the voice agent.

Next Steps