qelos-io/testai

Analysis updated 2026-05-18

★ 59TypeScriptAudience · developerComplexity · 2/5LicenseSetup · easy

Mindmap

mindmap
  root((TestAI))
    What it does
      Testing env builder
      Mock MCP servers
      Preset project fixtures
    Tech stack
      TypeScript
      Node.js 20+
      Vitest and Jest
    Use cases
      Agent testing
      MCP tool assertions
      Stack fixture testing
    Audience
      Developers building AI agents
    Status
      Presets return project handles
      Full test execution planned

mindmap root((TestAI)) What it does Testing env builder Mock MCP servers Preset project fixtures Tech stack TypeScript Node.js 20+ Vitest and Jest Use cases Agent testing MCP tool assertions Stack fixture testing Audience Developers building AI agents Status Presets return project handles Full test execution planned

What do people build with it?

USE CASE 1

Spin up a temporary test project fixture for a React, Nuxt, or FastAPI style stack.

USE CASE 2

Mock a service like Datadog, Slack, Figma, or Linear so a test can check which tools an agent called.

USE CASE 3

Compose a test environment around an existing project folder plus one or more MCP stubs.

USE CASE 4

Share a common testing setup across a team building AI agents and MCP servers.

What is it built with?

TypeScriptNode.jsVitestJest

How does it compare?

	qelos-io/testai	jlevy/tbd	owlinkai/redroom
Stars	59	59	59
Language	TypeScript	TypeScript	TypeScript
Setup difficulty	easy	moderate	hard
Complexity	2/5	2/5	4/5
Audience	developer	developer	researcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 30min

Requires Node.js 20 or newer.

Free to use, modify, and distribute, including commercially, as long as the copyright notice is kept.

In plain English

TestAI is a TypeScript library for testing software that is built around AI agents, tools, and related infrastructure such as MCP servers. It is meant to work alongside existing test runners like Vitest, Jest, or the plain Node test runner, rather than replace them, giving developers a shared set of building blocks for setting up test environments. The project is organized as three layers. The core package provides functions for creating a testing environment and a project, along with support for defining agents and mock MCP servers. A set of MCP stub packages simulate real services such as Datadog, Slack, Figma, and Linear, so a test can check which tools an agent called without needing the real service running. A set of preset packages provide ready made project fixtures for common stacks, including React, Nuxt, and FastAPI, each one handing back a temporary project a test can work with. A short code example in the README shows a test importing the core library along with a Datadog MCP stub and a Nuxt preset, creating a testing environment from either an existing folder on disk or a preset fixture, and then cleaning it up afterward. The README is honest that the project is still evolving. The preset factories currently create temporary directories and hand back a project object, while fuller behavior such as cloning a project, syncing its skills, and running a full test suite end to end is planned rather than finished. The repository requires Node.js version 20 or newer, is organized as a monorepo with separate folders for the core library, the MCP stubs, and the preset packages, and documentation is hosted at a dedicated site. The project is released under the MIT license.

Copy-paste prompts

Prompt 1

Show me how to set up a TestAI testing environment with the Datadog MCP stub.

Prompt 2

Help me write a Vitest test that uses TestAI's Nuxt preset project fixture.

Prompt 3

Explain what TestAI.createTestingEnv does and how to dispose of it after a test.

Prompt 4

Walk me through adding a new MCP stub package to a TestAI based test suite.

Frequently asked questions

What is testai?

A TypeScript library that gives AI agent and MCP projects reusable building blocks for tests, including mock services and preset project fixtures.

What language is testai written in?

Mainly TypeScript. The stack also includes TypeScript, Node.js, Vitest.

What license does testai use?

Free to use, modify, and distribute, including commercially, as long as the copyright notice is kept.

How hard is testai to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is testai for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.