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
IBM/AssetOpsBench
AssetOpsBench is an open framework from IBM Research for developing, orchestrating and evaluating domain-specific AI agents in industrial asset operations and maintenance. It packages reproducible scenarios covering nine asset classes and more than a hundred tasks, five domain agents and two orchestration frameworks, so multi-step agent workflows can be run and scored in simulated Industry 4.0 environments. Capabilities are exposed as domain-specific Model Context Protocol servers: an IoT server for sites, assets and installed or measured sensors; an FMSR server for retrieving and generating failure modes; a TSFM server whose 41 tools cover time series profiling, data quality checks, a model and feature catalog, recipe execution, evaluation and run or result lookup; a work order server for order distribution and next-order prediction; and a vibration server for FFT and envelope spectra. On top of these servers the repository ships several agent implementations: a plan-and-execute sequential runner that works with any LLM, a deep agent with planning, sub-agents and a virtual filesystem for long-horizon tasks, and ReAct-style orchestrators built on Claude and on OpenAI models that delegate to other agents as tools. The project combines large language models with time series foundation models over live sensor data and maintenance records such as FMEA reports, work orders and alerts. It targets maintenance engineers, reliability specialists, facility planners and Industry 4.0 researchers who need a common yardstick for agent behaviour in this domain. Installation is a pip editable install of the cloned repository, and scenarios are run through a command line module; a Colab notebook, a Hugging Face playground and a published dataset are also available. Active development happens on the main branch, while separate branches preserve the code used for individual publications.
https://github.com/IBM/AssetOpsBench
Also in Sensor Fusion Agents
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.
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.