https://github.com/agentlabs-dev/auto-inspector
Web Testing AI Agent - Write your specs, it does the rest
https://github.com/agentlabs-dev/auto-inspector
agentic-ai ai aiagent qa-automation webtesting
Last synced: about 2 months ago
JSON representation
Web Testing AI Agent - Write your specs, it does the rest
- Host: GitHub
- URL: https://github.com/agentlabs-dev/auto-inspector
- Owner: agentlabs-dev
- License: apache-2.0
- Created: 2025-02-04T19:31:48.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2025-02-14T13:47:33.000Z (2 months ago)
- Last Synced: 2025-02-14T14:38:35.171Z (2 months ago)
- Topics: agentic-ai, ai, aiagent, qa-automation, webtesting
- Language: TypeScript
- Homepage: https://magicinspector.com
- Size: 1.81 MB
- Stars: 155
- Watchers: 4
- Forks: 9
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-AI-driven-development - auto-inspector - Web Testing AI Agent - Write your specs, it does the rest (Uncategorized / Uncategorized)
README
.
Your Open-Source AI Web Testing Agent â Auto Inspector is an autonomous AI Agent that will test your website and give you a report of the results based on your user stories.
Auto Inspector is made by the Magic Inspector team to change the way web testing is done.
Focus on planning your tests, we run them for you.
.
đ Give us some love by starring this repository! đ
.
# Open-Source Web Testing AI Agent
Auto Inspector is fully open-sourced (Apache 2.0) and Magic Inspector offers cloud hosting and dedicated enterprise grade support.
## Demo
### GUI VERSION
https://github.com/user-attachments/assets/98881b79-eb63-4d10-aedf-f52ad64aecd5
### CLI VERSION
User story: I can log in to my account with '[email protected]' and 'demopassword' and create a new test inside the Default Project. Once the test has been created, I can see the test editor.
https://github.com/user-attachments/assets/7873f6a8-89d5-4234-8a17-0d993f5dc5c7
## How it works
## Getting Started
âšī¸ Note: Auto Inspector is currently in development and not ready to self-host. If you're looking for an enterprise-grade testing solution, check our **[Cloud Version](https://magicinspector.com)**.
Auto Inspector is available as a CLI utility and as a web application.
- The GUI web version is the easiest way to get started if you just to play with the agent.
- The CLI is probably more adapted to improve the agent and add new features to the core.
### GUI Version
#### Prerequisites
Before you begin, ensure you have the following installed on your machine:
- Docker
- Docker Compose
You can download Docker from [here](https://www.docker.com/products/docker-desktop) and Docker Compose from [here](https://docs.docker.com/compose/install/).
#### Clone the repository
```bash
git clone https://github.com/magic-inspector/auto-inspector.git
cd auto-inspector
```
#### Add your OpenAI API key in your .env file
```bash
echo OPENAI_API_KEY="" >> .env
```
#### Run the web application
```bash
make up
```
or to run in detached mode
```bash
make upd
make logs
```
This command will start the web application at `http://localhost`.
### CLI Version
#### Prerequisites
âšī¸ Note: Auto Inspector requires Node.js version 20 or higher.
#### Clone the repository and go to the backend folder
```bash
git clone https://github.com/magic-inspector/auto-inspector.git
cd auto-inspector/backend
npm install
```
#### Add your OpenAI API key
```
echo OPENAI_API_KEY="" >> .env
```
#### Run an example test case
```
npm run example:voyager
```
#### Run your own test case
```
npm run scenario -- --url="start-url" --user-story="As a user, I can "
```
## Roadmap for a stable release
We're committed to improving the project, feel free to open an issue if you have any suggestions or feedback.
| Component | Status | Features |
|:-------------------------|:------:|---------------------------------------------------------------------------------------------------------------------------------------------|
| Alpha release | â
ī¸ī¸ |
- Release a first minimap version that is able to run a test
| Add support for variables and secrets | â ī¸ī¸ |
- The agent can take variables and secrets from the user story
- Secrets are not displayed in the logs or sent to the LLM
| Run multiple cases from a test file | â ī¸ī¸ |
- Check the `npm run example:file` command for more information
| Interrupt actions when dom changes | â ī¸ |
- We need to interrupt the action if the interactives elements change after one action
| Wait page stabilized before evaluation | â ī¸ |
- Wait for the domContentLoaded event to be fired
- Wait for a minimal time to make sure the page is stable
| Manage completion at the action level | â ī¸ |
- We must manage completion at the action level instead of the task level to make sure the agent does not restart filling inputs over and over
| Update UI version to display steps in real-time | đī¸ |
- Update the UI to show the steps generated by the agent in real-time
| Add unit tests | đī¸ |
- Add vitest to test business logic
| Manager multiple tabs | đī¸ |
- We must listen to the tab events and manage the tabs
| Persist voyager results in file | đī¸ |
- we need to persist screenshots and results in a file for every test we run
| Refine user inputs | đī¸ |
- We must make sure that the Manager Agent and the Evaluation Agent get distinct inputs so the Manager Agent does not try to update its behavior based on the expected result
| Provide a GUI | đī¸ |
- Add docker configuration
- Add a simple UI to create a test
| Build a serious benchmark framework | đī¸ |
- The only serious way to improve the agent is to build a serious benchmark dedicated to the web testing.
| Add OpenAI YAML spec and generate frontend SDK dynamically | đī¸ |
- Automatically add OpenAI YAML specification
- Generate frontend SDK dynamically based on the specification
.
đ Give us some love by starring this repository! đ
.