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

Xpander.ai

Xpander.ai is an AI-agent runtime and control plane with a workbench for configuring agents, deployment options, and operational services such as stateful storage, logs and CI/CD.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Xpander.ai — 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 Xpander.ai when an agent project needs a shared workbench and deployment control plane, especially when choosing between managed serverless hosting and container-based execution.

Who it is for

  • Developers building agents with established frameworks or custom runtimes.
  • Teams that need to deploy and operate agents in managed cloud or customer-owned infrastructure.

Documented uses

  • Start an agent from a Starter Kit or framework and configure its prompt, model and tools.
  • Deploy an agent as a managed serverless service or an embedded container.
  • Operate deployed agents with stateful storage, logs and CI/CD.
  • Make agents available through Chat, webhooks, REST API, SDK, A2A or MCP.
Before you choose

Requirements & limits

The repository is public and specifies an MIT license. The documented platform setup begins with signing up and logging in at app.xpander.ai.

  • Managed Agents are described as serverless and require no infrastructure management; Embedded Agents use containers and provide control over frameworks and dependencies.
  • Both deployment modes are described as available in xpander cloud or a VPC/Kubernetes environment.
  • The platform identifies support for Agno, LangChain, PydanticAI, CrewAI and custom runtimes.
  • Agent use interfaces include Chat, webhook, REST API, SDK, A2A and MCP.

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

Create and deploy an embedded agent with the CLI

Set up a container-based agent project, run it locally and deploy it using the documented CLI sequence.

Before you start

  • Node.js/npm to install the xpander CLI
  • An xpander account for CLI login
  • Python 3 to create a virtual environment and install project requirements
  • A supported agent framework; the example uses Agno

Steps

  1. Install the CLI globally with npm install -g xpander-cli, then run xpander login.

  2. Create a project directory and initialize an agent with xpander agent new --name "hello-world" --framework agno --folder ..

  3. Create and activate a Python virtual environment, then install dependencies from requirements.txt.

  4. Run xpander dev for local execution, then use xpander deploy and xpander logs.

Expected outcome

A locally runnable embedded-agent project that can be deployed and inspected through the CLI.

Guide limitations

  • The example uses Agno and does not provide container image details or environment-specific deployment configuration.
  • The repository describes hosting in xpander cloud or VPC/Kubernetes but does not document the setup steps for those environments.
Documentation 1 ↗
Evidence and transparency

Sources & review

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