This repository provides an end-to-end reinforcement learning framework for StarCraft II gameplay research. The core agent uses Proximal Policy Optimization (PPO) to learn policy networks that interpret observation data from the PySC2 environment and output precise in-game actions. Developers can configure neural network layers, reward shaping, and training schedules to optimize performance. The system supports multiprocessing for efficient sample collection, logging utilities for monitoring training curves, and evaluation scripts for running trained policies against scripted or built-in AI opponents. The codebase is written in Python and leverages TensorFlow for model definition and optimization. Users can extend components such as custom reward functions, state preprocessing, or network architectures to suit specific research objectives.

Wizard Language is a declarative domain-specific language built on TypeScript for authoring AI assistants as wizards. Developers define intent-driven steps, prompts, tool invocations, memory stores, and branching logic in a concise DSL. Under the hood, Wizard Language compiles these definitions into orchestrated LLM calls, managing context, asynchronous flows, and error handling. It accelerates prototyping of chatbots, data retrieval assistants, and automated workflows by abstracting prompt engineering and state management into reusable components.

AnYi AI Agent Framework helps developers integrate autonomous AI agents into their applications. Agents can plan and execute multi-step tasks, leverage external tools and APIs, and maintain conversation context through configurable memory modules. The framework abstracts interactions with various LLM providers and supports custom tool and memory backends. With built-in logging, monitoring, and asynchronous execution, AnYi accelerates deployment of intelligent assistants for research, customer support, data analysis, or any workflow requiring automated reasoning and action.

AskAtlasAI-Agent empowers developers to deploy AI agents that answer natural language queries against any document set stored in MongoDB Atlas. It orchestrates LLM calls for embedding, search, and response generation, handles conversational context, and offers configurable prompt chains. Built on JavaScript/TypeScript, it requires minimal setup: connect your Atlas cluster, supply OpenAI credentials, ingest or reference your documents, and start querying via a simple API. It also supports extension with custom ranking functions, memory backends, and multi-model orchestration.

autogen4j is a lightweight Java library designed to abstract the complexity of building autonomous AI agents. It offers core modules for planning, memory storage, and action execution, letting agents decompose high-level goals into sequential sub-tasks. The framework integrates with LLM providers (e.g., OpenAI, Anthropic) and allows registration of custom tools (HTTP clients, database connectors, file I/O). Developers define agents through a fluent DSL or annotations, quickly assembling pipelines for data enrichment, automated reporting, and conversational bots. An extensible plugin system ensures flexibility, enabling fine-tuned behaviors across diverse applications.

The Controllable RAG Agent framework provides a modular approach to building Retrieval-Augmented Generation systems. It allows you to configure and chain retrieval components, memory modules, and generation strategies. Developers can plug in different LLMs, vector databases, and policy controllers to adjust how documents are fetched and processed before generation. Built on Python, it includes utilities for indexing, querying, conversation history tracking, and action-based control flows, making it ideal for chatbots, knowledge assistants, and research tools.

GenAI Processors provides a library of reusable, configurable processors to build end-to-end generative AI workflows. Developers can ingest documents, break them into semantic chunks, generate embeddings, store and query vectors, apply retrieval strategies, and dynamically construct prompts for large language model calls. Its plug-and-play design allows easy extension of custom processing steps, seamless integration with Google Cloud services or external vector stores, and orchestration of complex RAG pipelines for tasks such as question answering, summarization, and knowledge retrieval.

Janus Pro is a cutting-edge AI image generator that uses advanced models to create high-quality images from text descriptions. Built on DeepSeek-LLM architecture with 7 billion parameters, Janus Pro provides exceptional performance in both multimodal understanding and visual generation tasks. It leverages a novel autoregressive framework and separate encoding pathways to deliver superior image quality, detail, and accuracy. Available for free and open-source, Janus Pro is designed for ease of use, enabling users to transform their creative ideas into stunning visuals effortlessly.

Mina provides a lightweight yet powerful foundation for constructing AI agents in Python. You can define custom tools (such as web scrapers, calculators, or database connectors), attach memory buffers to maintain conversational context, and orchestrate sequences of calls to language models for multi-step reasoning. Built on top of common LLM APIs, Mina handles asynchronous execution, error handling, and logging out of the box. Its modular design makes it easy to extend with new capabilities, while the CLI interface enables quick prototyping and deployment of agent-driven applications.

Crewai provides a Python-based library to design and execute multi-AI agent systems. Users can define individual agents with specialized roles, configure messaging channels for inter-agent communication, and implement dynamic planners to allocate tasks based on real-time context. Its modular architecture enables plugging in different LLMs or custom models for each agent. Built-in logging and monitoring tools track conversations and decisions, allowing seamless debugging and iterative refinement of agent behaviors.

MS-Office-AI is an open-source Python framework that seamlessly integrates OpenAI’s GPT-3/GPT-4 models with Microsoft Office applications via the COM API. It provides developers and power users with a set of functions to automate content creation and data analysis inside Word, Excel, and PowerPoint. With simple method calls, you can generate full document drafts, summarize key points from existing text, auto-generate tables and charts based on natural language queries, and assemble structured slide decks. The package handles API communication, error management, and Office object model interactions, enabling you to focus on crafting prompts and workflows. Whether you need to draft reports, analyze datasets, or build presentations, MS-Office-AI accelerates your Office productivity by embedding AI directly into your familiar environment.

PremAI is an intuitive and privacy-centric Generative AI development platform. Designed for developers and enterprises, it facilitates the creation, deployment, and self-hosting of open-source AI models. The platform abstracts the complexities of AI, offering an easy-to-use interface for fine-tuning and training models. With rigorous standards in data retention and access control, it ensures privacy and security while enabling users to fully harness the power of AI.

Charstar AI is an innovative platform that enables users to interact with virtual characters. Utilizing the latest advancements in open-source AI, Charstar allows users to create and customize characters or choose from a wide range of predefined personalities. The platform supports rich chat experiences making it ideal for entertainment, companionship, and even customer service scenarios. With integrations for various third-party services, Charstar AI offers a flexible and engaging way to bring virtual characters to life.

Llama-Agent is a developer-focused toolkit for creating intelligent AI agents powered by large language models. It offers tool integration to call external APIs or functions, memory management to store and retrieve context, and chain-of-thought planning to break down complex tasks. Agents can execute actions, interact with custom environments, and adapt through a plugin system. As an open-source project, it supports easy extension of core components, enabling rapid experimentation and deployment of automated workflows across various domains.

MADDPG-Keras delivers a complete framework for multi-agent reinforcement learning research by implementing the MADDPG algorithm in Keras. It supports continuous action spaces, multiple agents, and standard OpenAI Gym environments. Researchers and developers can configure neural network architectures, training hyperparameters, and reward functions, then launch experiments with built-in logging and model checkpointing to accelerate multi-agent policy learning and benchmarking.

MAGAIL implements a multi-agent extension of Generative Adversarial Imitation Learning, enabling groups of agents to learn coordinated behaviors from expert demonstrations. Built in Python with support for PyTorch (or TensorFlow variants), MAGAIL consists of policy (generator) and discriminator modules that are trained in an adversarial loop. Agents generate trajectories in environments like OpenAI Multi-Agent Particle Environment or PettingZoo, which the discriminator uses to evaluate authenticity against expert data. Through iterative updates, policy networks converge to expert-like strategies without explicit reward functions. MAGAIL’s modular design allows customization of network architectures, expert data ingestion, environment integration, and training hyperparameters. Additionally, built-in logging and TensorBoard visualization facilitate monitoring and analysis of multi-agent learning progress and performance benchmarks.

multi_agent_celar is designed as a modular AI platform enabling emergent-language communication among multiple intelligent agents in simulated environments. Users can define agent behaviors via policy files, configure environment parameters, and launch coordinated training sessions where agents evolve their own communication protocols to solve cooperative tasks. The framework includes evaluation scripts, visualization tools, and support for scalable experiments, making it ideal for research on multi-agent collaboration, emergent language, and decision-making processes.