xlang-ai/OSWorld
OSWorld is a benchmarking platform for evaluating multimodal AI agents performing open-ended tasks in real computer environments using virtual machines and various virtualization technologies.
Awesome AI Agents › Sensor Fusion Agents
web-arena-x/webarena
WebArena is a standalone, self-hostable web environment designed for building and testing autonomous agents that can navigate and interact with web interfaces. It provides a realistic simulation of web environments, enabling researchers and developers to create agents that perform complex web navigation tasks autonomously. The project includes a comprehensive setup that mimics real-world web browsing scenarios, allowing agents to interact with various web elements such as buttons, links, and forms in a controlled environment. WebArena supports parallel experiments and integrates popular web navigation benchmarks, offering a unified framework for evaluation and leaderboard reporting. The environment is designed to be extensible and configurable, with support for custom websites and tasks, making it suitable for a wide range of research in autonomous web navigation and interaction. The repository provides detailed instructions for installation, setup, and usage, including environment configuration, test data generation, and evaluation procedures. It leverages modern tools and libraries to ensure code quality and maintainability, such as Python 3.10, pre-commit hooks, and type checking with mypy. Users can interact with the environment programmatically using a Gym-like API, facilitating the development and testing of AI agents. The project also offers resources like recorded human trajectories for benchmarking and an Amazon Machine Image with pre-installed websites for ease of deployment. WebArena is actively maintained and updated, with enhancements to its web navigation infrastructure through integration with AgentLab and BrowserGym. These improvements enable more efficient experimentation and better handling of edge cases. The project is supported by a research paper, a leaderboard for benchmarking agent performance, and community resources to foster collaboration and advancement in autonomous agent research. Overall, WebArena provides a robust platform for advancing the capabilities of autonomous agents in web-based environments.
https://github.com/web-arena-x/webarena
Also in Sensor Fusion Agents
IBM/AssetOpsBench
Open IBM framework and benchmark for building, orchestrating and evaluating domain-specific AI agents in industrial asset operations, with MCP servers over sensors, failure modes, time series and work orders.
google-deepmind/android_env
AndroidEnv is a Python library by DeepMind that provides a Reinforcement Learning platform by simulating Android devices, enabling agents to interact with real-world Android applications through touchscreen gestures for diverse RL tasks.
google-research/android_world
AndroidWorld is a comprehensive environment and benchmark for autonomous agents to interact with and control Android devices through a live emulator, featuring diverse tasks and integration with web-based benchmarks.
karanchawla/GPS_IMU_Kalman_Filter
An Extended Kalman Filter implementation that fuses GPS, IMU, and encoder sensor data to accurately estimate the pose of a ground robot in a navigation frame.
OSU-NLP-Group/TravelPlanner
TravelPlanner is a benchmark for evaluating language agents in real-world travel planning tasks involving complex tool use and multiple constraints.
StonyBrookNLP/appworld
AppWorld is a high-fidelity execution environment simulating a world of apps and people to benchmark and evaluate interactive coding agents through diverse and challenging autonomous tasks.
nottelabs/open-operator-evals
Open-operator-evals is an open-source benchmarking framework that evaluates the performance of web operators and agents using multiple metrics and a reproducible dataset to provide transparent and statistically sound comparisons.