AI Agents & Automation

Sage Towers is an innovative AI-driven massively multiplayer online (MMO) game that redefines the gaming experience through the integration of cutting-edge technologies like generative artificial intelligence and blockchain. Players can explore a dynamic universe populated by 'Living NPCs' with unique personalities and behaviors, ensuring every interaction feels genuine. The platform strongly emphasizes User Generated Content, empowering its community to shape their own adventures and foster an ecosystem built by players. With dynamically generated quests and evolving game worlds that respond to player actions, every playthrough offers a new adventure. Sage Towers also incorporates a player-influenced economy through its unique tokens and governance via a decentralized autonomous organization (DAO), allowing players to actively shape the game's future.

loki-mode is an open-source, multi-agent autonomous system designed to transform product requirements into production-ready code. It operates by classifying complexity, assembling agent teams from 41 specialized types across 8 swarms, and running autonomous RARV (Reason - Act - Reflect - Verify) cycles with 9 quality gates. The system ensures code quality through blind 3-reviewer code review and anti-sycophancy checks, only delivering code that passes automated verification. It supports 5 AI providers (Claude, Codex, Gemini, Cline, Aider) with automatic failover and outputs full-stack solutions including source code, tests, Docker configs, CI/CD pipelines, and audit logs. The tool is self-hosted and private, ensuring data privacy and no vendor lock-in.

The Multi-Agent-Medical-Assistant is an AI-powered chatbot designed to assist with medical diagnosis, research, and patient interactions. It leverages a multi-agent intelligence system, integrating Large Language Models (LLMs), Computer Vision Models for medical imaging analysis, Retrieval-Augmented Generation (RAG) with vector databases, and real-time Web Search for up-to-date medical insights. Key features include a multi-agent architecture for diagnosis and information retrieval, advanced RAG with Docling for document parsing, and confidence-based routing. It also offers medical imaging analysis for brain tumor detection, chest X-ray classification, and skin lesion segmentation, alongside voice interaction capabilities and human-in-the-loop verification for expert oversight.

QX innovates through rapid iteration and open-source solutions, focusing on deep-tech challenges in AI and blockchain. The platform aims to accelerate the refinement and accessibility of advanced technologies, making them adaptable and beneficial for everyday human and business needs. QX is actively constructing a human-centric software ecosystem designed to cater to enterprise needs, weaving together cutting-edge technology and open-source flexibility. Their offerings include a Blockchain-based Self-Sovereign Identity (SSI) system, a Web3 Custodial Wallet for loyalty programs, a digital QR menu for restaurants, and a customer experience dApp for shopping centers and retailers. They are also developing a utility token for Web3 loyalty programs and a Small Language Model (SLM) for friend chats.

RagaAI-Catalyst is a comprehensive Python SDK designed to enhance the management and optimization of LLM projects. It provides robust features for AI Agent observability, monitoring, and evaluation, including detailed tracing for agents, LLMs, and various tools. The platform facilitates debugging of complex multi-agent systems and offers a self-hosted dashboard with advanced analytics, featuring timeline and execution graph views. Key functionalities span project management, dataset management, evaluation management, trace management, prompt management, synthetic data generation, and guardrail management. This allows users to efficiently evaluate, optimize, and safeguard their LLM applications, ensuring transparency and performance in AI agent operations.

TinyTroupe is an experimental Python library developed by Microsoft for LLM-powered multiagent persona simulation. It enables users to create and simulate artificial agents, called TinyPersons, with customizable personalities, interests, and goals within simulated TinyWorld environments. Leveraging Large Language Models like GPT-4 and GPT-5, TinyTroupe generates realistic simulated behavior, focusing on understanding human behavior for productivity and business insights rather than direct AI assistance. Key applications include evaluating digital ads, providing test input for software, generating realistic synthetic data, offering feedback on product proposals from various personas, and simulating focus groups for brainstorming. The library is open-source and actively under development, with frequent updates to its API and features.

Morphik offers AI workers designed to automate back-office functions like accounts payable, payroll, and billing for multi-site healthcare operators. The platform learns existing workflows, GL codes, and approval chains to deploy custom AI workers trained on specific operational data. These AI workers handle tasks such as reading invoices, GL coding, routing approvals, and processing payments, allowing teams to focus on vendor management and cost reduction. Morphik aims to provide complete visibility and queryability of all documents and transactions across an entire operation, leading to significant annual savings and efficient deployment within weeks. It supports multi-site skilled nursing, senior living, and general healthcare facilities.

Cheetah Mobile (NYSE: CMCM) is a leading global mobile internet company and a pioneer in bringing Chinese mobile internet companies to the international market. The company leverages AI and big data to deliver exceptional mobile internet products worldwide, building a diversified product portfolio that includes tools, security, live streaming, and games. Cheetah Mobile is also deeply invested in artificial intelligence, possessing fully independently developed and industry-leading technologies in voice interaction, image recognition, and visual navigation. Their AI robot division, OrionStar, focuses on creating 'truly useful' robots for various applications, including reception, delivery, industrial logistics, and new retail services. Additionally, Cheetah Mobile offers comprehensive outbound advertising and cloud management services to help businesses expand globally.

Microsoft's agent-framework is a versatile, multi-language framework designed for building, orchestrating, and deploying AI agents and multi-agent workflows. It offers support for both Python and .NET implementations, enabling developers to create everything from simple chat agents to intricate graph-based orchestrations. Key features include graph-based workflows with streaming, checkpointing, human-in-the-loop, and time-travel capabilities. The framework also provides an interactive developer UI (DevUI) for agent development, testing, and debugging, along with built-in OpenTelemetry integration for observability. It supports various LLM providers and offers a flexible middleware system for request/response processing and exception handling. Experimental packages for benchmarking and reinforcement learning are available through AF Labs.

EverWorker is an AI platform designed to accelerate businesses by providing an AI workforce that integrates seamlessly, automates tasks, and enhances productivity without requiring complex engineering. It offers end-to-end AI solutions to accelerate time-to-market, increase revenue, and gain a competitive edge. The platform features AI Workers, AI Workflows, and a No-Code Creator, allowing users to build custom AI workers for any unique business workflow using plain language. EverWorker provides out-of-the-box AI solutions for various business functions, including Sales & Marketing, HR & Recruiting, Customer Success & Support, and Finance & Operations, which can be quickly customized and deployed in hours. It's built for business and operations professionals, enabling them to transform ideas into impact, innovate with limitless capacity, and effortlessly scale AI Agents across their organization.

VirtuE, an innovation center focused on HumanTech, offers a platform of Humankind Solutions, including proprietary Affective Computing. This technology enables AI solutions to deeply understand and appropriately respond to human emotions, moving beyond simple data processing to more nuanced interactions. The platform provides essential tools for advanced simulation, utilizing virtual humans to test and refine AI's emotional intelligence. VirtuE also offers a comprehensive platform to manage connections with various AI solutions, ensuring seamless integration and operation within diverse applications. This focus on emotional intelligence in AI positions VirtuE as a key player in developing more empathetic and human-centric artificial intelligence.

Freedom.AI is a Brazilian platform offering AI agents designed to transform various business areas by automating operations. It specializes in developing custom multi-agents capable of handling repetitive tasks and complex processes across financial, legal, and AI vision domains. The platform emphasizes data governance and seamless integration with existing client systems, operating within the client's firewall for enhanced security. Freedom.AI aims to enable scalable AI implementation with speed and security, providing a robust solution for companies looking to leverage artificial intelligence for operational efficiency and task execution.

X07 is a programming language and comprehensive toolchain designed to facilitate the creation of dependable software by AI agents. It addresses common programming ambiguities by offering canonical APIs, structured diagnostics, and deterministic repair loops, significantly reducing guesswork and errors in agent-generated code. The language prioritizes memory-safe defaults, speed, explicit concurrency, and predictable deployment, making it suitable for systems programming. X07 supports a coherent story from local edit to release review, covering CLIs, services, MCP servers, WASM, and packages. It aims to provide both humans and agents with the same contracts, ensuring consistency from code review to CI and release operations. The ecosystem includes tools for building MCP servers, WASM applications, and a lifecycle platform for deployment, monitoring, and repair.

Launch AI Agent Swarm for ARC-AGI-3 provides a platform for deploying and managing a collaborative swarm of AI agents designed to autonomously play ARC-AGI-3 games. Users can submit their AI agent strategies using Claude Code or Codex, allowing them to experiment with multi-agent systems and test new AI architectures. The platform features a live leaderboard to track agent performance and contributions, fostering a competitive environment for AI development. It aims to democratize access to sophisticated AI experimentation, making multi-agent system development more accessible for developers, researchers, and AI enthusiasts interested in advancing artificial general intelligence.

Awesome-AI-Agents is a comprehensive, open-source collection of autonomous agents powered by Large Language Models (LLMs). This repository serves as a valuable resource for developers and researchers interested in AI agents, offering a wide array of applications, task solver projects, and multi-agent systems. It covers various aspects from individual autonomous agents like AutoGPT and gpt-engineer to multi-agent frameworks such as MetaGPT and ChatDev. Beyond applications, it delves into agent society simulations, advanced components like memory systems and communication protocols, and essential tools and frameworks for agent development. The collection also includes benchmarks, evaluators, platforms, APIs, and related research papers, making it a central hub for exploring and building with AI agents.

KAWA AI offers an agentic operating system designed for enterprise operations, enabling organizations to build and deploy AI systems for high-stakes tasks. It automates mission-critical workflows using governed AI agents, deterministic orchestration, and comprehensive control. The platform integrates with existing systems like SAP, Salesforce, and APIs, unifying them into a structured layer. Key capabilities include a no-code workflow builder, an enterprise AI agent builder with operational guardrails, and custom application development for areas like reconciliation, risk monitoring, and compliance. KAWA AI emphasizes enterprise-grade security, governance, and human-in-the-loop controls, ensuring AI agents operate within defined policies and provide full audit trails.

awesome-LangGraph serves as a comprehensive index for the LangChain and LangGraph ecosystem, offering a curated collection of frameworks, templates, and real-world projects. It is designed for teams aiming to build, observe, evaluate, and deploy stateful, tool-using AI agents. The repository covers the full lifecycle of agent development, from core libraries and integrations to platform tooling for observation, evaluation, and reliable deployment. It features core frameworks like LangChain, LangGraph, Deep Agents, and LangSmith, alongside integrations, official projects, community projects categorized by use case (e.g., RAG, web automation, finance), starter templates, and learning resources. This makes it an invaluable resource for both prototyping and operating production-grade agent systems.

Eigent AI offers Eigent Open Source Cowork, a desktop multi-agent workforce designed to automate real work by connecting to your context and controlling browser and desktop applications. This tool leverages multi-agent collaboration to handle complex tasks, boosting productivity. As a research-driven startup, Eigent AI focuses on building infrastructure for multi-agent ecosystem systems, including the open-source LLM-based multi-agent framework CAMEL-AI. Its core offering, the Open Source Cowork, acts as a general-purpose agent that integrates seamlessly with your desktop environment to streamline workflows and automate repetitive or intricate operations.

Neura Dynamics offers comprehensive AI consulting services and full-stack development to empower businesses with generative AI. They specialize in building scalable enterprise AI, automating workflows, and delivering end-to-end development solutions. Their services include AI consulting, AI product development, AI/ML development, intelligent automation, and full-stack development. They cater to both startups and enterprises, helping them transform ideas into intelligent digital products through advanced AI consulting, software engineering, and modern product design. Neura Dynamics focuses on delivering high-impact solutions with a startup-friendly approach, offering on-demand AI talent and specialized AI expertise.

Apex.AI offers a comprehensive suite of SDKs, AI-powered tools, and expert services designed to accelerate the transition to modern software development, particularly for AI and autonomous systems. Their product lineup includes Apex.Grace for managing embedded software execution with precision, Apex.Ida for high-speed, fault-tolerant data flow across systems, and Apex.Alan for automated tools and CI/CD workflows. They also provide Apex.OS for Verification and Validation, a data recording and replay system for precise testing. Beyond products, Apex.AI offers services like technical assessments, strategy definition, embedded and cloud software development, CI/CD pipeline implementation, and ROS 1 to ROS 2 migration, catering to industries such as automotive, agriculture, medical, and defense.

CandyCall is an innovative AI-driven platform that allows users to send humorous prank calls featuring over 300 celebrity AI voices. Unlike traditional pre-recorded prank calls, CandyCall utilizes AI voice technology to facilitate dynamic conversations, where the AI responds and reacts to the person on the other end of the line. This ensures a more interactive and entertaining experience. Users can choose from iconic voices like Joe Biden, Donald Trump, Kanye West, and Elon Musk. The platform also offers a Pro version that allows users to upload their own voice for a personalized prank. CandyCall aims to provide a fun and affordable alternative to other prank call services, emphasizing its AI-powered conversational capabilities.

UnixClaw offers a lightweight and secure AI assistant solution for Mac Mini users, adopting a 'Unix Way' philosophy for AI automation. It differentiates itself from complex AI agent systems by emphasizing simplicity, transparency, and user control, thereby mitigating security risks and unpredictable behavior often associated with opaque, overly autonomous agents. Built with small, single-purpose C tools connected by Unix pipes, UnixClaw allows for individual understanding and testing of each component. It supports local inference on Apple Silicon Macs, ensuring zero cost per token and keeping data on the machine. The system integrates with native macOS apps like Calendar, Reminders, Contacts, and Notes, enabling the AI to interact with real data and sync across devices without complex APIs or cloud dependencies. This approach provides a straightforward, scriptable AI helper that prioritizes user control and system integrity.

myclaude is a multi-agent orchestration workflow system designed for AI-powered development automation. It integrates with various AI backends including Claude, Codex, Gemini, and OpenCode, allowing for flexible and powerful code creation and development. The tool offers several modules like 'do' for 5-phase feature development, 'omo' for intelligent multi-agent routing, and 'bmad' for agile workflows with specialized agents. It also provides essential development commands for tasks such as bug fixing, code generation, debugging, and optimization. myclaude is highly configurable, enabling users to select and enable specific modules and skills to tailor the workflow to their project needs, making it a versatile solution for developers seeking to automate and enhance their coding processes.

EnsoAI is a desktop application designed to enhance developer workflows by enabling multiple AI agents to operate in parallel within a single Git project. It treats each Git branch as a first-class workspace with its own dedicated AI context, allowing seamless switching between agents like Claude, Codex, Gemini, Cursor, Droid, and Auggie. The tool integrates a visual source control interface for reviewing diffs, staging changes, and managing commits, alongside a built-in Monaco editor for quick edits. Key features include AI-powered code review, auto-generated commit messages, a 3-way merge tool, and robust Git worktree management. EnsoAI is not a full IDE replacement but rather a lightweight workspace manager that can bridge to other IDEs like VS Code or Cursor for deeper development.