diff --git a/README.md b/README.md index 874950f5..ba482291 100644 --- a/README.md +++ b/README.md @@ -43,6 +43,7 @@ BrowserGym includes the following benchmarks by default: - [WorkArena](https://github.com/ServiceNow/WorkArena) - [AssistantBench](https://github.com/oriyor/assistantbench) - [WebLINX](https://github.com/McGill-NLP/weblinx) (static benchmark) + - [OpenApps](https://facebookresearch.github.io/OpenApps/) Designing new web benchmarks with BrowserGym is easy, and simply requires to inherit the [`AbstractBrowserTask`](https://github.com/ServiceNow/BrowserGym/blob/main/browsergym/core/src/browsergym/core/task.py#L7C7-L7C26) class. @@ -72,6 +73,7 @@ Finally, each benchmark comes with its own specific setup that requires to follo - for VisualWebArena, see [visualwebarena/README.md](browsergym/visualwebarena/README.md) - for WorkArena, see [WorkArena](https://github.com/ServiceNow/WorkArena) - for AssistantBench, see [assistantbench/README.md](browsergym/assistantbench/README.md) + - for OpenApps, see [OpenApps docs](https://facebookresearch.github.io/OpenApps/) ### 🏗️ Development setup @@ -178,6 +180,17 @@ env_ids = [id for id in gym.envs.registry.keys() if id.startswith("browsergym/wo print("\n".join(env_ids)) ``` +OpenApps +```python +from open_apps.apps.start_page.main import app # need to import apps to serve +from open_apps.launcher import OpenAppsLauncher + +config = ... # configure a namespace with task, agent, envrionment, and server configs + +launcher = OpenAppsLauncher(config) +launcher.launch() +``` + ## 💻 Demo If you want to experiment with a demo agent in BrowserGym, follow these steps