Open-source alternatives to Malmo

Qwen-Agent is a development framework for building autonomous software applications that leverage large language models to plan, reason, and execute complex tasks. It functions as an orchestration engine that enables models to interact with external APIs, manage persistent memory, and maintain context across multi-step workflows. The framework distinguishes itself through a multi-agent collaboration platform that allows independent agent instances to exchange structured messages and delegate sub-tasks to one another. By utilizing iterative reasoning loops and dynamic prompt injection, the sys

AgentMemory is a persistent knowledge store and memory server designed to provide AI coding agents with long-term memory. It functions as a knowledge graph engine and vector database store that saves and recalls project context, architectural decisions, and patterns across different sessions. The system distinguishes itself by using a tiered-memory consolidation pipeline that compresses raw observations into episodic, semantic, and procedural layers to optimize token usage. It employs a hybrid retrieval strategy combining keyword matching, vector embeddings, and graph traversal to surface rel

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Mindcraft is a framework for connecting large language models to game clients to create autonomous characters that communicate and perform actions within a simulated environment. It functions as an orchestrator for bots, utilizing a system that bridges high-level AI instructions with low-level game protocol packets to enable the execution of in-game tasks. The system uses retrieval-augmented generation to select relevant conversation history and code examples via embedding-based context retrieval. It supports the development of specific AI personas through profile configurations and facilitat

Lab is a customizable 3D platform and research testbed designed for training and testing autonomous agents using reinforcement learning. It serves as a spatial AI training simulator where agents can be evaluated through navigation and puzzle-solving tasks. The environment allows for the definition of complex layouts and task behaviors through external scripting, enabling the generation of specific challenges for AI research. It supports both automated training via standard API bindings and manual agent control to validate simulation dynamics. The system utilizes a grid-based spatial represen

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 is an educational repository of reinforcement learning agents and tutorials implemented using TensorFlow. It provides a practical codebase for both model-free and model-based learning agents, designed to demonstrate how AI agents learn through trial and error. The collection features detailed implementations of various algorithmic approaches, including Deep Q-Networks and Policy Gradient methods. It specifically covers Actor-Critic architectures for continuous and discrete action spaces, alongside Proximal Policy Optimization and Deep Deterministic Policy Gradients. The framewor

Open Spiel is a research library and framework for reinforcement learning, planning, and multi-agent game simulation. It provides a system for representing single-agent and multi-agent games across zero-sum, cooperative, and imperfect information scenarios. The project utilizes a standardized abstract game interface to decouple game logic from algorithms, allowing agents to run across different game types. It implements performance-critical logic in C++ with Python bindings and uses deterministic seeded simulation to ensure reproducibility for research benchmarking. The framework covers a br

This project is a Python voxel game engine and real-time renderer designed for interacting with block-based 3D environments. It functions as a procedural terrain simulator and a first-person navigator, allowing users to explore and visualize worlds composed of individual cubes. The system enables direct procedural terrain manipulation, providing a mechanism to add or remove blocks in real time to create custom structures. It utilizes a first-person camera system to translate keyboard and mouse inputs into movement and perspective changes within the virtual space. The engine handles 3D space

Star-Office-UI is a visual workspace and dashboard designed to map the activity and work states of AI agents to characters and zones within a virtual office. It functions as a multi-agent status monitor that tracks external entities via join keys and a desktop overlay application that renders a persistent, transparent window on the computer desktop. The project distinguishes itself through an integrated AI background generator that uses image generation APIs to create and update the virtual environment. It also includes a markdown activity logger that reads and displays sanitized daily summar

This project is a wave function collapse generator and voxel environment engine used for procedural world generation. It implements a constraint-based layout algorithm to resolve superpositions of modules into consistent 3D voxel grids. The system functions as a procedural city generator capable of creating infinite, walkable urban environments. It utilizes a dynamic dictionary to stream map data as a user approaches new areas, ensuring a continuous world without loading the entire layout at once. The engine manages layout consistency through adjacency rule definitions, boundary constraint e

DouZero is a deep reinforcement learning framework and training system designed to teach digital agents to master complex card games. It provides the infrastructure to implement high-throughput reinforcement learning pipelines and evaluate the competitive success of game agents. The system utilizes a distributed actor-learner architecture that separates game simulation actors from GPU training devices to accelerate model convergence. It combines Monte Carlo Tree Search with policy-based value estimation to determine optimal moves through recursive evaluation and random sampling. The toolkit

PocketFlow is a graph-based framework for designing and executing large language model operations and reasoning patterns. It serves as an orchestrator for building goal-oriented autonomous agents, multi-agent systems, and retrieval-augmented generation pipelines. The system is distinguished by its ability to coordinate autonomous AI agents that use shared memory and tools to solve complex goals, supported by a structured output engine that enforces schema-consistent responses. It utilizes graph-based workflow orchestration to manage sequences of model operations and supports supervisor-based

Grasscutter is a private game server emulator designed to replicate game backend logic and simulate core gameplay mechanics without the use of official servers. It functions as a system for simulating character progression, world entities, and general backend simulation to host a private instance of a specific anime game. The project includes a game object management console for spawning entities and controlling player inventories within the simulated environment. It also provides a server configuration tool featuring a guided interface to generate and manage the settings and configuration fi

ClawTeam is a framework for coordinating multiple large language model agents to automate complex technical workflows. It operates as an agentic workflow automator and orchestrator that manages swarms of specialized agents using a leader-worker architecture to delegate and execute tasks. The system distinguishes itself by providing isolated workspaces for parallel development, assigning each agent a dedicated git worktree and branch to prevent merge conflicts. It further enables the integration of external command-line tools by wrapping them into a standardized input and directory execution m

pysc2 is a Python interface and simulation framework that connects the StarCraft II game engine to machine learning agents. It acts as an API wrapper that exposes game internals as a set of observations and actions, providing a reinforcement learning environment for research and training. The framework includes tools for game replay analysis to extract data and sequences of actions from recorded matches for predictive modeling. It also provides an agent simulation environment to run and evaluate the performance of single or competing artificial intelligence agents. The system handles game ma

This project is an AI agent workflow orchestrator and automated software lifecycle manager designed to sequence specialized AI personas for end-to-end software development. It serves as a prompt engineering library and a full-stack development toolkit that guides the process from initial discovery and specification through to deployment and code review. The system features a context management framework that utilizes progressive loading and routing tables to fetch reference files on-demand, reducing token consumption within the model context window. It employs a definition-based routing syste

Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist

LazyLLM is a multi-agent framework and orchestration engine designed for building complex AI applications. It provides a system for chaining large language models into sequential or parallel pipelines, utilizing a tool registry to convert standard functions into discoverable tools that models can invoke via reasoning. The project features an application deployment kit that enables hosting model workflows as web services with integrated chat interfaces and API gateways. It includes an infrastructure abstraction layer that allows users to switch between bare-metal servers, clusters, and public

minecraft-weekend is a voxel engine designed for rendering infinite three-dimensional environments. It utilizes procedural generation and mathematical noise functions to automate the creation of diverse landscapes, biomes, and height variations. The engine implements a voxel rendering system using buffer-based meshes and chunk-based world partitioning to manage GPU performance and memory usage. It includes a dynamic lighting system that calculates light values, transparency, and distance-based fog to simulate atmospheric depth. The project covers 3D game physics simulation through axis-align

The Arcade Learning Environment is a research-focused platform that provides a high-performance emulation engine for Atari 2600 games. It serves as a standardized environment for training and evaluating artificial intelligence agents, bridging native game execution with machine learning libraries through a dedicated Python interface. The project distinguishes itself by offering robust support for parallel and vectorized environment execution, allowing multiple game instances to run simultaneously to accelerate data collection. It includes specialized tools for asynchronous command queuing and

Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge

CrewAI is a multi-agent orchestration framework designed for building autonomous systems that execute complex, multi-step workflows. It provides a development platform where specialized agents are defined with specific roles, goals, and tool sets to perform tasks collaboratively. By leveraging a declarative workflow engine, the system manages task dependencies, state transitions, and execution logic, allowing for the creation of structured, stateful sequences of operations. The framework distinguishes itself through its hierarchical management capabilities, which utilize manager agents to coo

This project provides a comprehensive framework for building, deploying, and orchestrating autonomous agents within a decentralized network. It serves as a collection of patterns and examples for developing intelligent software entities capable of performing complex tasks, making decisions, and interacting with other agents to achieve shared goals. The framework distinguishes itself through its focus on multi-agent orchestration and decentralized communication. It enables the coordination of specialized agent teams that collaborate on workflows through structured messaging protocols, allowing

Cline is an extensible agent runtime and multi-agent orchestration engine designed to automate complex software engineering workflows. It functions as an integrated development environment extension that bridges strategic task planning with autonomous execution, allowing users to manage multi-step projects through human-in-the-loop oversight or independent agent operation. The platform distinguishes itself by enabling the creation of specialized agent teams that share a common state and coordinate through a centralized task manager. It enforces project-specific architectural guidelines and co

ChatDev is an automated software engineering platform that orchestrates the end-to-end development lifecycle through a multi-agent framework. It functions as a programmable engine that coordinates specialized autonomous agents to handle design, coding, testing, and documentation tasks by transitioning through predefined phases of a software project. The system distinguishes itself by using role-based agent specialization to simulate a professional engineering team, assigning distinct personas and knowledge bases to individual agents. It employs prompt-driven task decomposition to break high-l

Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut