{"id":25499263,"url":"https://github.com/agentlabs-dev/auto-inspector","last_synced_at":"2025-11-11T09:30:18.498Z","repository":{"id":276314009,"uuid":"927333095","full_name":"agentlabs-dev/auto-inspector","owner":"agentlabs-dev","description":"Web Testing AI Agent - Write your specs, it does the rest","archived":false,"fork":false,"pushed_at":"2025-02-14T13:47:33.000Z","size":1895,"stargazers_count":155,"open_issues_count":2,"forks_count":9,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-02-14T14:38:35.171Z","etag":null,"topics":["agentic-ai","ai","aiagent","qa-automation","webtesting"],"latest_commit_sha":null,"homepage":"https://magicinspector.com","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/agentlabs-dev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-04T19:31:48.000Z","updated_at":"2025-02-14T13:50:24.000Z","dependencies_parsed_at":"2025-02-14T14:38:36.030Z","dependency_job_id":null,"html_url":"https://github.com/agentlabs-dev/auto-inspector","commit_stats":null,"previous_names":["magic-inspector/auto-inspector","agentlabs-dev/auto-inspector"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlabs-dev%2Fauto-inspector","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlabs-dev%2Fauto-inspector/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlabs-dev%2Fauto-inspector/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlabs-dev%2Fauto-inspector/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agentlabs-dev","download_url":"https://codeload.github.com/agentlabs-dev/auto-inspector/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239587204,"owners_count":19663892,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-ai","ai","aiagent","qa-automation","webtesting"],"created_at":"2025-02-19T03:01:42.124Z","updated_at":"2025-11-11T09:30:18.449Z","avatar_url":"https://github.com/agentlabs-dev.png","language":"TypeScript","funding_links":[],"categories":["TypeScript","Testing \u0026 Security"],"sub_categories":["Other IDEs"],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://magicinspector.com\"\u003e\u003cimg src=\"./.readme/cover.png\" alt=\"Magic Inspector\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003cem\u003e.\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp align=center\u003e\nYour Open-Source AI Web Testing Agent — 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.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\nAuto Inspector is made by the \u003ca href=\"https://magicinspector.com\"\u003eMagic Inspector\u003c/a\u003e team to change the way web testing is done.\n\u003c/p\u003e\n\n\u003cp align=center\u003e\nFocus on planning your tests, we run them for you.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/License-Apache 2.0-blue.svg\" alt=\"License version\"\u003e\n\u003c/a\u003e\n\u003ca href=\"\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Status-Under Active Development-green.svg\" alt=\"Docker Image CI\"\u003e\n\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n.\n\u003c/p\u003e\n\n\u003ch3 align=\"center\"\u003e\n🌟 Give us some love by starring this repository! 🌟  \n\u003c/h3\u003e\n\n\u003cp align=\"center\"\u003e\n.\n\u003c/p\u003e\n\n\n# Open-Source Web Testing AI Agent\n\nAuto Inspector is \u003cb\u003efully open-sourced (Apache 2.0)\u003c/b\u003e and \u003ca href=\"https://magicinspector.com\"\u003eMagic Inspector\u003c/a\u003e offers cloud hosting and dedicated enterprise grade support.\n\n\n## Demo \n\n### GUI VERSION\n\nhttps://github.com/user-attachments/assets/98881b79-eb63-4d10-aedf-f52ad64aecd5\n\n### CLI VERSION\n\nUser story: I can log in to my account with 'demo@magicinspector.com' and 'demopassword' and create a new test inside the Default Project. Once the test has been created, I can see the test editor.\n\nhttps://github.com/user-attachments/assets/7873f6a8-89d5-4234-8a17-0d993f5dc5c7\n\n## How it works\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://magicinspector.com\"\u003e\u003cimg src=\"./.readme/how-it-works.png\" alt=\"agentlabs.dev\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n## Getting Started\n\nℹ️ 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)**.\n\nAuto Inspector is available as a CLI utility and as a web application.\n- The GUI web version is the easiest way to get started if you just to play with the agent.\n- The CLI is probably more adapted to improve the agent and add new features to the core.\n\n### GUI Version\n\n#### Prerequisites\n\nBefore you begin, ensure you have the following installed on your machine:\n\n- Docker\n- Docker Compose\n\nYou can download Docker from [here](https://www.docker.com/products/docker-desktop) and Docker Compose from [here](https://docs.docker.com/compose/install/).\n\n\n#### Clone the repository\n\n```bash\ngit clone https://github.com/magic-inspector/auto-inspector.git\ncd auto-inspector\n```\n\n#### Add your OpenAI API key in your .env file\n\n```bash\necho OPENAI_API_KEY=\"\u003creplace-with-your-key\u003e\" \u003e\u003e .env\n```\n\n#### Run the web application\n\n```bash\nmake up\n```\n\nor to run in detached mode\n\n```bash\nmake upd\nmake logs\n```\n\nThis command will start the web application at `http://localhost`.\n\n\n### CLI Version\n\n#### Prerequisites\n\nℹ️ Note: Auto Inspector requires Node.js version 20 or higher.\n\n\n#### Clone the repository and go to the backend folder\n\n```bash\ngit clone https://github.com/magic-inspector/auto-inspector.git\ncd auto-inspector/backend\n\nnpm install\n```\n\n#### Add your OpenAI API key\n\n```\necho OPENAI_API_KEY=\"\u003creplace-with-your-key\u003e\" \u003e\u003e .env\n```\n\n#### Run an example test case\n\n```\nnpm run example:voyager\n```\n\n#### Run your own test case\n\n```\nnpm run scenario -- --url=\"start-url\" --user-story=\"As a user, I can \u003creplace-with-your-user-story\u003e\"\n```\n\n## Roadmap for a stable release\n\nWe're committed to improving the project, feel free to open an issue if you have any suggestions or feedback.\n\n| Component                | Status | Features                                                                                                                                    |\n|:-------------------------|:------:|---------------------------------------------------------------------------------------------------------------------------------------------|\n| Alpha release       |  ✅️️   | \u003cul\u003e\u003cli\u003eRelease a first minimap version that is able to run a test\u003c/li\u003e\u003c/ul\u003e      \n| Add support for variables and secrets       |  ✅️️    | \u003cul\u003e\u003cli\u003eThe agent can take variables and secrets from the user story\u003c/li\u003e\u003cli\u003eSecrets are not displayed in the logs or sent to the LLM\u003c/li\u003e\u003c/ul\u003e \n| Run multiple cases from a test file       |  ✅️️    | \u003cul\u003e\u003cli\u003eCheck the `npm run example:file` command for more information\u003c/li\u003e\u003c/ul\u003e \n| Interrupt actions when dom changes |  ✅️  | \u003cul\u003e\u003cli\u003eWe need to interrupt the action if the interactives elements change after one action\u003c/li\u003e\u003c/ul\u003e\n| Wait page stabilized before evaluation |  ✅️   | \u003cul\u003e\u003cli\u003eWait for the domContentLoaded event to be fired\u003c/li\u003e\u003cli\u003eWait for a minimal time to make sure the page is stable\u003c/li\u003e\u003c/ul\u003e \n| Manage completion at the action level  | ✅️   | \u003cul\u003e\u003cli\u003eWe 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\u003c/li\u003e\u003c/ul\u003e\n| Update UI version to display steps in real-time | 🏗️   | \u003cul\u003e\u003cli\u003eUpdate the UI to show the steps generated by the agent in real-time\u003c/li\u003e\u003c/ul\u003e\n| Add unit tests  | 🏗️   | \u003cul\u003e\u003cli\u003eAdd vitest to test business logic\u003c/li\u003e\u003c/ul\u003e\n| Manager multiple tabs  | 🏗️   | \u003cul\u003e\u003cli\u003eWe must listen to the tab events and manage the tabs\u003c/li\u003e\u003c/ul\u003e \n| Persist voyager results in file       |  🏗️   | \u003cul\u003e\u003cli\u003ewe need to persist screenshots and results in a file for every test we run\u003c/li\u003e\u003c/ul\u003e     \n| Refine user inputs       |  🏗️   | \u003cul\u003e\u003cli\u003eWe 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\u003c/li\u003e\u003c/ul\u003e                                                             |\n| Provide a GUI |    🏗️   | \u003cul\u003e\u003cli\u003eAdd docker configuration\u003c/li\u003e\u003cli\u003eAdd a simple UI to create a test\u003c/li\u003e\u003c/ul\u003e |\n| Build a serious benchmark framework      |  🏗️  | \u003cul\u003e\u003cli\u003eThe only serious way to improve the agent is to build a serious benchmark dedicated to the web testing.\u003c/li\u003e\u003c/ul\u003e     \n| Add OpenAI YAML spec and generate frontend SDK dynamically | 🏗️   | \u003cul\u003e\u003cli\u003eAutomatically add OpenAI YAML specification\u003c/li\u003e\u003cli\u003eGenerate frontend SDK dynamically based on the specification\u003c/li\u003e\u003c/ul\u003e\n\n\n\n\n\n\u003cp align=\"center\"\u003e\n.\n\u003c/p\u003e\n\n\u003ch3 align=\"center\"\u003e\n🌟 Give us some love by starring this repository! 🌟  \n\u003c/h3\u003e\n\n\u003cp align=\"center\"\u003e\n.\n\u003c/p\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentlabs-dev%2Fauto-inspector","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagentlabs-dev%2Fauto-inspector","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentlabs-dev%2Fauto-inspector/lists"}