Projects sharing features with Universe

ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and compute orchestrator. It enables the improvement of multi-step agent reasoning and tool usage through group relative policy optimization and a judge-based reward modeling system. The project features tools for model distillation to transfer capabilities from large teacher models to smaller architectures, as well as a system for capturing execution trajectories to generate synthetic training data. It supports specialized training workflows including supervised fine-tuning for baselin

OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language models as agents. It serves as an agentic reasoning optimizer and reward model trainer, providing the infrastructure to improve model decision-making through reward-based policy optimization. The project distinguishes itself through a distributed architecture that supports parameter sharding across multiple compute nodes and a coordinated rollout system for collecting interaction trajectories. It incorporates advanced reasoning strategies, such as Tree-of-Thoughts and Monte Ca

Gymnasium is a suite of standardized APIs and simulation toolkits used to evaluate agent behavior and benchmark reinforcement learning algorithms. It provides a standardized interface for creating and interacting with simulated environments, enabling the training of reinforcement learning agents through a consistent set of interaction protocols. The project emphasizes experimental reproducibility through a versioned API and a system for tracking changes to environment logic using version suffixes. This ensures that learning results remain consistent and can be replicated across different soft

OSWorld is an evaluation framework and multimodal agent benchmark designed to test the ability of large language models to complete complex tasks within virtualized operating system environments. It provides a virtualized desktop sandbox and a virtual machine orchestrator to deploy, snapshot, and reset cloud-based desktops, ensuring reproducible test states for AI agent interactions. The system distinguishes itself by providing an OS-level action space that translates model decisions into mouse clicks, keyboard inputs, and system commands. It employs a standardized interface to integrate vari

This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This

Verifiers is a reinforcement learning environment framework and evaluation toolkit designed to train and evaluate large language models. It provides a standardized system for constructing simulation environments, managing training harnesses, and tracking agent trajectories through multi-turn interactions. The project features a dedicated agent trajectory manager to handle branching rollouts and token sequences, alongside an evaluation toolkit that tests model outputs against defined reward rubrics and datasets. It includes capabilities for reward engineering and the ability to package environ

Agent Lightning is an optimization framework designed to refine the performance of individual AI agents within complex multi-agent systems. It provides a platform for improving decision-making and task execution by applying reinforcement learning, supervised fine-tuning, and automated prompt optimization. The framework distinguishes itself through its ability to isolate specific agents for targeted tuning, allowing developers to enhance individual behaviors while maintaining the stability of the broader system architecture. By utilizing a modular interface, it integrates with diverse agent fr

Gym is a reinforcement learning environment toolkit and agent simulation framework. It provides a standardized API and a universal communication interface that defines how learning agents interact with simulation environments through actions and observations. The project includes a benchmark environment suite and a diverse library of pre-configured simulation worlds, including physics engines and classic control tasks. It enables the creation of custom simulation environments to train agents in specific operational scenarios while ensuring reproducibility across different learning algorithms.

This project provides a comprehensive framework for building, training, and managing autonomous agents. It enables the construction of systems that utilize language models to plan, manage memory, and execute multi-step tasks through iterative reasoning loops and tool-based actions. The framework distinguishes itself by offering specialized capabilities for interacting with graphical user interfaces and legacy software, allowing agents to perceive visual elements and perform actions like a human user. It supports complex, cross-application workflows through graph-based orchestration and provid

This project is a reinforcement learning toolkit and simulation-based AI trainer for creating intelligent agents within Unity simulations. It provides a multi-agent simulation framework for configuring cooperative or competitive scenarios and includes an environment wrapper that bridges simulations with standard machine learning libraries using gym-style interfaces. The system features a native cross-platform inference engine that executes trained neural network models for real-time decision making without external dependencies. It enables the acceleration of the learning process by running m

mcp-agent is a framework for building AI agents that integrate with Model Context Protocol servers to execute tools and access data. It functions as a multi-agent orchestrator and protocol-compliant server, enabling the creation of agents that can discover and invoke tools from connected external servers. The project distinguishes itself through a durable workflow engine that supports long-running tasks capable of pausing, resuming, and surviving restarts. It implements complex orchestration patterns, including iterative evaluator-optimizer loops, hierarchical workflow nesting, and specialist

Kilocode is an autonomous engineering platform designed to orchestrate AI agents for complex software development tasks. It functions as a comprehensive system for automating coding, testing, and repository management by integrating directly with your codebase and terminal. The platform provides a unified gateway for model orchestration, allowing for the management of agentic workflows, event-driven automation, and persistent session state across distributed development environments. The platform distinguishes itself through its federated task management and policy-based access control, which

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

Letta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across long-term interactions. It provides a comprehensive suite of primitives for defining agents with configurable personas, modular memory blocks, and tool-use capabilities, enabling them to retain user preferences and conversation history over extended sessions. The platform distinguishes itself through its advanced memory management and orchestration capabilities. It allows agents to autonomously update their own memory, perform retrieval-augmented generation, and coordinate com

This project is a comprehensive deep reinforcement learning course and training platform. It provides a structured educational curriculum that combines theoretical lessons with hands-on tutorials to teach the implementation of neural networks and agent behavior. The platform integrates a model sharing hub where users can upload, download, and version trained machine learning models. It also features a benchmarking system that uses leaderboards to evaluate and compare agent performance against community standards. The educational experience is delivered through interactive notebooks and inclu

PyGame Learning Environment is a Python framework that provides a standardized interface for training artificial intelligence agents within diverse game environments. It functions as a communication layer that bridges reinforcement learning agents with game state observations, action inputs, and reward signals, allowing for consistent interaction across different game titles. The platform distinguishes itself by offering a headless execution mode that disables graphical rendering pipelines. By bypassing display overhead, this feature accelerates training cycles for automated agents during bac

IsaacGymEnvs is a GPU-accelerated physics sandbox and robotics policy training suite designed for reinforcement learning. It serves as a vectorized robotic simulator that runs thousands of parallel environments on GPUs to accelerate the training of neural networks. The project provides a sim-to-real transfer framework that utilizes domain randomization and physics variations to ensure policies trained in simulation are robust enough for deployment on real hardware. It distinguishes itself through a high-performance architecture that uses tensor-based state management to handle observations an

This project is a game AI training framework designed to develop and monitor reinforcement learning agents within a legacy game environment. It functions as a training and monitoring system that optimizes autonomous agents to complete game objectives through exploration and reward-based learning. The framework includes tools for game memory mapping and real-time trajectory visualization. These capabilities translate raw game memory addresses into visual coordinates, allowing agent movements and session data to be streamed to a map for the analysis of navigation patterns and area exploration.

Capybara is a browser automation library and web application acceptance test framework used to simulate user behavior and verify functional requirements. It serves as a cross-browser testing tool and headless browser orchestrator, allowing for the execution of test suites across multiple browser engines. The project provides a driver-agnostic interaction layer that abstracts different browser engines, enabling users to switch between headless and full browser drivers. It supports multi-user session simulation by maintaining independent browser states and cookies to test interactions between i

Ragas is an evaluation framework designed to measure the performance of retrieval-augmented generation pipelines and autonomous agent workflows. It provides a comprehensive suite of tools for benchmarking system outputs, utilizing language models as automated judges to score performance against defined rubrics and reference data. By standardizing inputs, retrieved contexts, and generated responses into a unified schema, the project enables consistent analysis across complex AI applications. The framework distinguishes itself through its ability to generate synthetic test datasets from existin

Cua is an agent benchmarking and desktop automation platform designed to evaluate autonomous agents and execute repetitive tasks within isolated, virtualized environments. It provides a framework for provisioning consistent workspaces and measuring agent performance against standardized desktop operations. The platform distinguishes itself by integrating virtual machine orchestration with headless interaction capabilities. By leveraging hypervisor-based virtualization, it runs operating systems at near-native speeds, while its automation layer injects commands directly into application proces

Stable-baselines3 is a reinforcement learning library built on the PyTorch deep learning framework. It provides a collection of reliable, standardized implementations of reinforcement learning algorithms designed for training, testing, and benchmarking agent policies in diverse simulated environments. The library functions as an agent training toolkit that emphasizes modularity and reproducibility. It features a unified environment interface and supports vectorized execution to accelerate data collection across multiple simulation instances. Users can customize neural network architectures, f

This project is a comprehensive framework for the entire lifecycle of transformer-based language models, supporting everything from foundational pretraining to specialized deployment. It provides a modular toolkit for defining neural network architectures, managing data preparation pipelines, and executing training routines across various scales. The framework is designed to handle the full model development process, including supervised fine-tuning, behavioral alignment, and the integration of agentic capabilities. What distinguishes this framework is its focus on efficient training and adva

KIF is a functional testing framework and UI automation tool for iOS. It enables the simulation of user interactions and the verification of application states by driving interface components through their defined accessibility attributes. The framework utilizes an actor-pattern action wrapper to group reusable interaction sequences and allows the definition of custom, high-level test steps through a method-extension action library. It performs in-process interface driving, interacting with the application directly within the same process to execute actions and validate view states. The tool

Codeception is a full-stack testing framework for PHP applications that provides a unified interface for unit, functional, and acceptance testing. It serves as a tool for automating real desktop and mobile browsers via the WebDriver protocol and acts as a client for testing REST and SOAP APIs. The framework is distinguished by its support for Behavior-Driven Development, allowing users to write human-readable test specifications in Gherkin language to align technical tests with business requirements. It implements actor-based action mapping to connect these natural language steps to executabl

OpenWhisk is a serverless cloud platform designed for deploying and executing stateless functions in response to API calls or events. It serves as a complete serverless stack, providing an API gateway for functions, a function-as-a-service runtime manager, and an event-driven workflow engine. The platform distinguishes itself through a polyglot execution model that supports multiple language runtimes and allows for the creation of custom runtimes using Docker containers. It enables complex logic through function orchestration and composition, allowing multiple functions to be chained into seq

BackstopJS is an automated screenshot testing framework and visual regression testing tool designed to identify pixel-level discrepancies between different versions of a web application. It functions as a browser automation testing suite that captures visual snapshots of a user interface and compares them against stored reference images to detect unintended changes. The project utilizes a containerized testing environment via Docker to ensure consistent browser rendering and prevent cross-platform visual discrepancies. It includes a web UI diffing interface that allows users to analyze visual