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
google-research/android_world
AndroidWorld is an environment and benchmark designed for autonomous agents to interact with and control Android devices. It operates on a live Android emulator and offers a comprehensive benchmark consisting of 116 hand-crafted tasks across 20 real-world applications. These tasks are dynamically instantiated with randomly generated parameters, enabling millions of unique task variations. The environment supports reliable evaluation through durable reward signals and provides an open platform with access to millions of Android apps and websites. AndroidWorld is lightweight, requiring only 2 GB of memory and 8 GB of disk space, and is designed to be extensible, allowing users to add new tasks and benchmarks easily. It also integrates with the MiniWoB++ web benchmark, which includes web-based tasks rendered as native Android UI widgets, challenging agents to use universal widgets like time and date pickers. The project includes detailed installation instructions, including setting up an Android emulator, installing dependencies, and configuring environment variables for model provider APIs. Users can run a variety of tasks, resume interrupted runs, and create their own agents by extending provided base classes. The environment is suitable for research and development in autonomous computer control agents, providing a reproducible and scalable platform for benchmarking agent performance on diverse and complex tasks within the Android ecosystem.
https://github.com/google-research/android_world
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.
web-arena-x/webarena
WebArena is a self-hostable web environment designed for building and evaluating autonomous agents capable of realistic web navigation and interaction tasks.
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.
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.