AI Agents & Automation

Arbiter is a Rust-based, event-driven multi-agent framework designed for orchestrating strongly-typed, high-performance simulations and networked systems. It provides foundational types and traits for building actor-based systems with pluggable networking and lifecycle management. Tailored for discrete-event simulation, automated trading, and complex distributed systems, Arbiter's core concepts include Actors for execution units, LifeCycle for actor behavior, Handlers for message processing, Networks for system connections, and Runtimes for managing execution context. The framework is open-source and actively developed by Harnesslabs, offering extensive documentation and examples for in-depth understanding.

CRSLab is an open-source toolkit designed for building Conversational Recommender Systems (CRS), developed using Python and PyTorch. It offers a robust framework with comprehensive benchmark models and datasets, including graph neural network and pre-training models like R-GCN, BERT, and GPT-2. The toolkit supports extensive and standard evaluation protocols for testing and comparing different CRS, and features a general and extensible structure for unifying various conversational recommendation datasets and models. CRSLab also provides human-machine interaction interfaces for qualitative analysis, making it easy for new researchers to get started with flexible configurations.

Infermedica provides a medically certified AI triage platform designed to enhance patient care navigation and streamline healthcare operations. It offers solutions for public health, government, health plans, insurers, healthcare providers, telemedicine companies, and pharmaceutical companies. The platform includes conversational AI for digital front door triage, AI-powered decision support for call centers and nurse triage, and pre-visit intake to collect structured patient data. Infermedica is certified as a Class IIb medical device under EU MDR and ISO 13485:2016 for medical devices, ensuring high standards of compliance, security, and data governance, including GDPR, HIPAA, and SOC 2 Type 2®.

The Beijing Institute for General Artificial Intelligence (BIGAI) is a non-profit research institution established with the support of the Beijing municipal government and the Ministry of Science and Technology. Collaborating with prestigious institutions like Peking University and Tsinghua University, BIGAI is dedicated to advancing general artificial intelligence. The institute focuses on fundamental research to create AI agents capable of autonomous perception, cognition, decision-making, and social collaboration. BIGAI also engages in talent development through programs such as a joint doctoral program and an undergraduate experimental class in general artificial intelligence.

ContestTrade is an innovative open-source multi-agent trading framework designed to help users build their own AI trading teams. It operates without manual intervention, automatically scanning the entire market for potential event-driven investment opportunities based on news, announcements, capital flows, and policies. The system employs a two-stage internal contest mechanism: first, data analysis agents refine raw market data into structured 'text factors,' and then research agents, with their unique 'trading beliefs,' analyze these factors to generate trading proposals. A second contest evaluates these proposals to synthesize a unified, reliable asset allocation strategy. Users can customize research preferences and strategies, and configure API keys for LLMs and data sources like Tushare or AKShare.

Hugging Multi-Agent is a comprehensive tutorial designed for developers interested in understanding and implementing multi-agent systems, particularly those based on the MetaGPT framework. It offers a practical learning path, guiding users from foundational agent concepts to the development of complex multi-agent applications. The tutorial is ideal for engineers aiming for career advancement in large language model and agent development, focusing on hands-on coding and personalized agent capabilities. It requires Python programming skills, including some asynchronous programming knowledge, and the ability to read and understand project source code. The resource covers agent structure, multi-agent frameworks, and practical development steps, including creating simple and multi-functional agents, as well as managing agents.

PrivateBlok is an AI platform specifically designed for private markets, offering a comprehensive suite of tools that integrate data, intelligence, and customizable workflows. The platform leverages a sophisticated Multi-Agent System to efficiently manage various financial workflows. It incorporates both public and proprietary data sources to provide robust insights. A key feature is its AI Co-pilot, which assists users with critical functions such as investment intelligence, investor reporting, and portfolio tracking, making it a valuable asset for professionals in the private market sector.

ForU AI is a platform dedicated to building a proof-based reputation system for both human contributors and AI agents within the AI economy. Its core mission is to establish a trust layer, enabling the verification of contributors and securing communities. The platform analyzes patterns and traits to generate user profiles, aiming to provide a reliable and verifiable identity for participants in AI-driven ecosystems. This system is designed to foster trust and accountability, which are crucial for the widespread adoption and integration of AI technologies across various sectors.

Honda Research Institute Europe (HRI-EU) is a leading research institution dedicated to innovation through science, particularly in the fields of Artificial Intelligence and intelligent systems. Their core focus is on Cooperative Intelligence, aiming to develop systems that work effectively among, for, and with humans. Research areas include cooperative behavior, data analytics, learning, ethics in AI, perception, knowledge representation, personalization, human-machine interaction, prediction, risk assessment, and system optimization. HRI-EU also explores applications in intelligent adaptive cruise control, ergonomics for robots, and energy management. The institute collaborates with academic and industrial partners, fostering a vibrant research environment for PhD and Master students.

General Reasoning is an AI R&D company dedicated to building infrastructure for long horizon AI capabilities. The company focuses on developing advanced AI models that can manage complex, long-term tasks across various domains. Their work involves creating robust systems that can adapt and learn over extended periods, aiming to enhance operational efficiencies and support sustainable growth through autonomous technology deployment. Key initiatives include the release of Firehorse and research into KellyBench, demonstrating their commitment to pushing the boundaries of reinforcement learning and AI agent development. They also offer Harbor Environments on OpenReward, providing tools for practical application and research.

TradingAgents-CN is a Chinese-enhanced version of the revolutionary multi-agent LLM-based financial trading framework, TradingAgents. Designed for learning and research, it helps users systematically understand how to use multi-agent trading frameworks and large AI models for compliant stock research and strategy experimentation. The platform does not provide real-time trading instructions, focusing instead on educational and research purposes. It features native OpenAI and Google AI support, custom endpoint configurations, intelligent model selection, and multi-LLM provider support. The tool also offers Docker containerized deployment, professional report export capabilities, and comprehensive support for A-share stocks, along with full Chinese localization.

Cultivation World Simulator is an open-source project designed to simulate a Xianxia (immortal hero) world using AI Agent workflows. It allows users to act as 'Heavenly Dao' and observe a dynamic world where each cultivator is an independent AI agent with unique personalities, memories, relationships, and decision-making logic. The simulator integrates complex rules for cultivation, sects, artifacts, and events, guiding AI behavior within a rich logical framework. This approach leads to emergent narratives, ensuring an unpredictable and evolving world. It supports Docker for easy deployment and offers an API for external control, making it suitable for both developers and those interested in observing an AI-driven fantasy world.

python-a2a is a Python library designed to implement Google's Agent-to-Agent (A2A) protocol. This protocol enables seamless communication and interaction between various AI agents, fostering the development of interoperable agent ecosystems. The library aims to simplify the process of building complex multi-agent systems where different AI entities can collaborate on tasks and exchange information effectively. It provides the foundational tools necessary for developers to create robust and scalable agent-based applications, allowing agents to work together to solve intricate problems and achieve common goals. The design prioritizes both power and ease of use, making it accessible for developers looking to integrate advanced agent communication capabilities into their projects.

pytorch-DRL is an open-source project offering PyTorch implementations for various Deep Reinforcement Learning (DRL) algorithms. It is designed to be modular, allowing for efficient code sharing and reusability across different algorithms. The project supports both single-agent and multi-agent learning environments, making it versatile for a wide range of research and development in reinforcement learning. Included algorithms cover popular methods such as A2C, DQN, DDPG, and PPO, providing a solid foundation for developers and researchers working on AI agents and automation. Its focus on PyTorch makes it accessible to those familiar with the framework, facilitating rapid prototyping and experimentation in DRL.

Spleenlab specializes in developing next-generation AI software for autonomous systems across various industries, including aviation, automotive, defense, and robotics. Their solutions are designed to enable safe, scalable, and certifiable automation. For drones, Spleenlab offers capabilities such as GPS-denied navigation, surveillance, collision avoidance, precision landing, and terrain-following. For vehicles, their AI software supports multi-object detection, sensor fusion, freespace detection, occupancy grids, and GPS-denied SLAM. The company's product suite, VISIONAIRY®, includes modules for camera calibration, spatial detection, object detection, navigation, and localization, all compatible with various hardware, chips, and sensors. SPLEENLAB® Suite further provides video stabilization, an operating system, AI runtime, and simulation tools, ensuring efficient performance with minimal computational resources.

VirtualHome is an interactive platform and API designed for simulating complex household activities using programs. It enables multi-agent simulations where agents can interact with environments by picking up objects, switching appliances, and more. The platform offers two simulators: the Unity Simulator for generating videos of activities and the Evolving Graph simulator for tracking environmental changes. It supports various ground-truth streams like time-stamped actions, segmentation, and optical flow, making it suitable for training agents in embodied AI tasks. VirtualHome also features procedural generation for unique environments, enhanced physics, time management, and improved lighting, with a Python API for easy integration and control.

claude-sub-agent is a comprehensive AI-driven development workflow system built on Claude Code's Sub-Agents feature. It automates the entire software development lifecycle, from requirements analysis to final validation, by employing specialized AI agents. Each agent, such as `spec-analyst`, `spec-architect`, and `spec-developer`, handles specific aspects of the process, ensuring specialized expertise. The system incorporates quality gates at various phases to maintain high standards and provides comprehensive documentation for every step. It offers flexible integration, allowing it to work with existing specialized agents, and supports quick starts with slash commands for initiating workflows and customizing parameters like quality thresholds or skipping agents.

Neuronic Systems specializes in providing advanced technology modules designed for defense integrators. Their core offering includes seamless connectivity solutions for various unmanned systems such as UAVs, drones, UGVs, and USVs, as well as diverse sensor systems. The company delivers intellectual property, sophisticated algorithms, and sub-systems that are ready for integration into prime defense platforms. This focus on robust, interconnected systems ensures high-performance and reliable operations in critical defense applications. Neuronic Systems aims to enhance the capabilities of defense platforms through its specialized AI-powered solutions and integration expertise.

AgentForge is a powerful open-source AI agent framework designed for building, customizing, and deploying cognitive architectures and multi-agent systems. It allows developers to create specialized AI agents tailored to specific requirements through its flexible architecture. Users can integrate various tools and define custom actions to enhance agent capabilities, along with sophisticated persona management to define agent personalities and behaviors. The framework supports flexible storage options for maintaining agent state and managing data efficiently. AgentForge also provides comprehensive APIs for connecting with external services and a wide range of helper utilities to streamline agent development. It is ideal for use cases such as customer service, research assistance, content creation, process automation, synthetic data generation, and custom chatbot development.

JazzX AI is an AI execution platform built specifically for the mortgage industry, aiming to automate and optimize the entire mortgage lifecycle. It goes beyond generic AI tools by providing governed, end-to-end automation that leads to audit-ready decisions, faster cycle times, and reduced costs per loan. The platform ensures every decision is backed by full-file reasoning with traceable, source-cited findings, eliminating idle queues and compressing cycle times. JazzX AI also focuses on accelerating pipeline conversion through a guided borrower and loan officer experience, and unifies various personas, workflows, and data layers above existing systems to prevent tool sprawl.

Artifice is a real-time multiplayer strategy game specifically designed for AI agents to compete for dominance. Users can observe AI agents engaging in warfare, forming alliances, and executing betrayals in a turn-based combat system. The platform offers a unique arena to test and showcase the strategic capabilities and decision-making processes of various AI models. It features a leaderboard to track agent performance, a replay function for past battles, and a 'How to Play' guide for understanding the game mechanics. Artifice serves as an engaging environment for developers and enthusiasts to analyze and compare AI agent behaviors in a dynamic, competitive setting.

Bigdatamatica Solutions Pvt Ltd is an AI solutions provider focused on delivering enterprise-grade applications. The company specializes in advanced areas such as agentic AI, quantum intelligence, and real-time decision systems. Their solutions are designed to help businesses unlock valuable insights from their data, eliminate operational inefficiencies, and accelerate innovation across various sectors. Bigdatamatica aims to provide comprehensive data-to-deployment intelligence platforms, catering to industries like retail and mobility, enabling them to leverage cutting-edge AI and automation technologies for strategic advantage.

Agentic Data Analysis with Claude Code is a multi-agent system designed to automate and enhance the data analysis workflow using Claude's capabilities. It takes a question about a dataset, analyzes the data through a series of subagents, and generates an interactive report. The system includes a table-finder subagent to identify relevant tables, table-reader subagents for initial research loops (query generation, execution, and analysis), and table-report subagents to design charts and generate TypeScript for the report. A report-orchestrator consolidates findings into a React web app, and chart-qa subagents identify and fix issues in generated charts. This system aims to deliver comprehensive data analysis, though it currently requires incremental improvements for hypothesis generation and general data intuition.

HKB Tech is an AI and DeepTech company dedicated to fostering global growth through advanced AI solutions. Their core expertise lies in patented Agentic AI/ML and proprietary DeepTech intellectual property. The company focuses on delivering strategic projects and solutions for a diverse clientele, including government entities, large-scale mega-projects, and various enterprises across multiple sectors. HKB Tech aims to leverage its specialized AI capabilities to address complex challenges and drive innovation in different industries.