Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -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.

Expand Down Expand Up @@ -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

Expand Down Expand Up @@ -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
Expand Down