Awesome GitHub RepositoriesAgent Simulation Environments

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.

Generative Agents is a computational platform for simulating autonomous agents that exhibit human-like social behaviors and decision-making processes. The system functions as a multi-agent simulator where individual participants operate within a virtual environment, driven by large language models to process observations and generate natural language actions. The framework distinguishes itself through a hierarchical memory system that allows agents to store, retrieve, and synthesize past experiences into higher-level insights. This architecture supports the development of complex social dynam

DeepResearch is an autonomous research agent framework designed to orchestrate multi-step information gathering and complex reasoning tasks. The platform functions as an agent orchestration system that manages the entire lifecycle of autonomous research, from initial planning and web navigation to the synthesis of evidence-backed reports. The framework distinguishes itself through a specialized training pipeline that supports the development and fine-tuning of autonomous models using reinforcement learning and structured knowledge graph synthesis. By employing parallel agent coordination, the

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

This project is an AI research implementation library and machine learning research repository. It provides a collection of reference code, illustrative implementations, and open-source research datasets used to verify hypotheses and build upon existing models in artificial intelligence. The repository focuses on scientific research reproduction by translating theoretical findings from published papers into executable code. It includes specialized scientific simulation environments designed to test the behavior of autonomous agents and models within controlled settings. The project covers AI

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

ParlAI is a conversational AI research framework designed for training, evaluating, and sharing dialogue models using a unified interface for datasets and agents. It functions as a PyTorch-based training platform and a dialogue data collection system, providing a centralized model zoo for the distribution of versioned pretrained agents. The project distinguishes itself through a knowledge-grounded retrieval system that combines dense and sparse indexing to ground responses in external information. It also provides a comprehensive infrastructure for gathering human-AI interaction data via inte

pysc2 este o interfață Python și un framework de simulare care conectează motorul jocului StarCraft II la agenți de machine learning. Acționează ca un wrapper API care expune elementele interne ale jocului ca un set de observații și acțiuni, oferind un mediu de reinforcement learning pentru cercetare și antrenament. Framework-ul include instrumente pentru analiza reluărilor de joc pentru a extrage date și secvențe de acțiuni din meciurile înregistrate în scopul modelării predictive. De asemenea, oferă un mediu de simulare a agenților pentru a rula și evalua performanța agenților de inteligență artificială singuri sau în competiție. Sistemul gestionează configurarea hărților de joc, analiza comportamentală și oferă o interfață de control manual pentru depanarea comportamentului agenților. Transformă starea jocului în tensori multidimensionali și utilizează un framework de apelare de proceduri la distanță (RPC) pentru a gestiona comunicarea între client și motorul jocului.

TinyTroupe is a multi-agent simulation framework designed to create populations of persona-based agents that interact to generate synthetic behavioral data and business insights. It serves as a persona-based agent orchestrator and synthetic data generator, allowing for the definition of agents with specific personality traits and goals to coordinate their interactions through structured workflows. The project features an extensible plugin system for connecting simulated agents to external tools and servers to execute code and access remote data. It includes an agentic simulation dashboard tha

rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T

Evolve is an evolution-based organism designer and GPU-accelerated artificial life simulator that combines interactive particle physics with a real-time simulation editor. At its core, it runs genetic algorithm evolution on self-replicating graph structures to evolve digital organisms, offloading particle physics, neural networks, and rendering entirely to the GPU through a compute shader pipeline for real-time performance. The project distinguishes itself with graph-based organism design that uses a directed graph editor to visually define organism structure, connections, and neural controll

Agentverse este un framework multi-agent și un orchestrator conceput pentru implementarea și gestionarea mai multor agenți de modele de limbaj mari. Oferă un mediu de simulare în care agenții interacționează pe baza unor personaje personalizate și a unor reguli de interacțiune definite pentru a rezolva sarcini sau a simula dinamici sociale. Sistemul dispune de un strat de integrare a instrumentelor care conectează agenții la plugin-uri funcționale externe și instrumente specializate, extinzându-le capabilitățile dincolo de generarea de text. Utilizează o combinație de injectare de prompt-uri bazată pe personaje și memorie gestionată de stare pentru a menține consistența agenților și seturile de abilități specializate în timpul simulărilor. Framework-ul include un runtime de simulare și un motor de sarcini cu un dashboard web local pentru executarea și monitorizarea scenariilor. Suportă provizionarea mediului bazată pe configurație pentru a defini comportamentul agenților, rutarea mesajelor și orchestrarea bazată pe ture.

Oasis is an LLM-powered multi-agent social simulator and research tool designed to study synthetic social phenomena. It functions as a synthetic social network platform, replicating the infrastructure of social sites including user profiles, follow relationships, and content discovery mechanisms to model human-like social behaviors at scale. The framework orchestrates large-scale agent populations, supporting up to one million autonomous agents. It distinguishes itself by translating language model outputs into concrete social actions and external tool executions through a tool-calling orches

SLIME is a distributed reinforcement learning framework for large language model post-training that bridges Megatron training with SGLang inference servers. It orchestrates scalable RL loops across GPU clusters, decoupling training and inference into independent processes that communicate over HTTP and NCCL for independent scaling and fault tolerance. The system supports multi-agent reinforcement learning workflows with parallel agent instances, customizable rollout strategies, and personalized agent serving that improves models from prior conversations without disrupting API serving. The fra

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

Habitat-sim is a high-performance 3D simulation platform designed for training and benchmarking embodied AI agents within photorealistic indoor and outdoor environments. It serves as a simulator for AI and robotics, providing a system for generating synthetic data and simulating physical interactions. The project is distinguished by a native C++ core that enables high-throughput simulation and a rendering pipeline using physically based rendering and baked global illumination. It features a navigation system based on pre-computed navigation meshes to ensure collision-free traversal and a rigi

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

ModelingToolkit.jl este un framework de modelare simbolică și un sistem de algebră computațională conceput pentru definirea și simularea sistemelor matematice complexe. Oferă un mediu fundamental pentru construirea modelelor fizice multi-domeniu și a sistemelor de ecuații diferențiale, permițând utilizatorilor să reprezinte probleme științifice prin grafuri simbolice care facilitează analiza și transformarea automatizată. Framework-ul se distinge prin compoziția sa de componente acauzale, care permite asamblarea modelelor la scară largă prin conectarea elementelor modulare în loc de definirea fluxurilor de date explicite. Utilizează ruperea automată a sistemului și reducerea indicelui pentru a simplifica ecuațiile diferențiale-algebrice complexe, asigurând stabilitatea numerică. Prin utilizarea compilării simbolice just-in-time, sistemul mapează aceste definiții de nivel înalt direct în cod mașină optimizat pentru execuție de către solvere numerice specializate. Dincolo de simularea standard, proiectul integrează utilitare de machine learning științific pentru a combina modelele fizice simbolice cu rețelele neuronale. Suportă descoperirea automată a ecuațiilor, permițând extragerea structurilor matematice guvernante din date experimentale. Framework-ul include, de asemenea, instrumente cuprinzătoare pentru optimizarea numerică, inclusiv generarea automată a derivatelor și exploatarea rarității, pentru a accelera rezolvarea sistemelor la scară largă.