AI Agents & Automation

PromptCraft-Robotics is an open-source repository and community dedicated to exploring and sharing applications of large language models (LLMs) within the robotics domain. It features a sample robotics simulator, built on Microsoft AirSim, which integrates with ChatGPT, allowing users to test natural language commands for robotic tasks. While primarily focused on OpenAI's ChatGPT, the platform welcomes contributions and examples from other LLMs like GPT-3 and Codex. Users can contribute by submitting interesting prompt examples across various robotics categories such as Manipulation, Home Robotics, and Aerial Robotics, fostering a collaborative environment for innovation in LLM-driven robotics.

Qwen is an open-source large language model developed by Alibaba Cloud, providing a suite of models including Qwen-1.8B, Qwen-7B, Qwen-14B, and Qwen-72B, along with their chat-optimized versions. These models are pretrained on trillions of tokens of multilingual data, focusing on Chinese and English, and demonstrate competitive performance across various benchmark datasets. Qwen supports functionalities like chatting, content creation, information extraction, summarization, translation, coding, and mathematical problem-solving. It also offers capabilities for tool usage, acting as agents, and code interpreters. The repository provides resources for quick inference, quantization details, finetuning tutorials (full-parameter, LoRA, Q-LoRA), and deployment instructions for platforms like vLLM and FastChat.

Ragapp provides the easiest way to implement Agentic RAG (Retrieval-Augmented Generation) within any enterprise setting. It is designed for straightforward configuration, mirroring the user-friendly experience of OpenAI's custom GPTs, but with the added benefit of being deployable directly into your own cloud infrastructure using Docker. Built upon LlamaIndex, Ragapp supports both hosted AI models like OpenAI and Gemini, as well as local models via Ollama. The tool exposes an Admin UI for configuration, a Chat UI for interaction, and an API for programmatic access. It emphasizes security by integrating with existing API Gateways for authentication and plans to support authorization based on access tokens in future versions. Deployment is flexible, offering Docker Compose setups (with Ollama and Qdrant, or multiple RAGapps with a management UI) and upcoming Kubernetes support.

Ralph Orchestrator is an open-source framework designed for autonomous AI agent orchestration, implementing the "Ralph Wiggum technique" for continuous iteration until a task is completed. It features a unique hat-based system where specialized personas coordinate through events, and includes backpressure gates to reject incomplete work. The tool supports multiple AI backends such as Claude Code, Kiro, Gemini CLI, Codex, Amp, and Copilot CLI. It offers persistent learning through memories and tasks, and includes built-in functions like code-assist, debug, research, and review. A web dashboard is available for monitoring and managing orchestration loops, and human-in-the-loop interaction is supported via Telegram, allowing agents to ask questions and humans to provide proactive guidance.

AutoMem is a graph-vector memory service designed to give AI assistants durable, relational memory. Unlike traditional RAG or vector databases, AutoMem stores typed relationships and embeddings, allowing for nuanced recall beyond keyword matching. It scores highly on long-term memory benchmarks like LoCoMo. The service combines FalkorDB for graph storage and Qdrant for vector embeddings, offering a hybrid query system that considers semantic similarity, graph traversal, temporal alignment, tag overlap, and importance. It features neuroscience-inspired memory consolidation cycles, strengthening important memories and allowing less relevant ones to fade. AutoMem is suitable for self-hosting via Docker or Railway and supports integration with various AI clients like Claude, Cursor, and ChatGPT.

ServerlessLLM is a system designed for efficient and cost-effective deployment of multiple AI models on shared GPU resources. It features ultra-fast checkpoint loading, achieving 6-10x faster model loading than SafeTensors by using a custom storage format and O_DIRECT I/O. The tool also offers GPU multiplexing, allowing multiple models to share GPUs with rapid switching and intelligent scheduling, and supports auto-scaling and live migration. Furthermore, ServerlessLLM integrates LLM serving with serverless LoRA fine-tuning, enabling on-demand deployment of fine-tuned adapters and efficient serving of base models with hundreds of LoRA adapters. It provides an OpenAI-compatible API and supports both NVIDIA and AMD GPUs, making it suitable for production environments.

CrewAI is a leading multi-agent platform designed to accelerate AI agent adoption and deliver production value for enterprises. It simplifies the operation of teams of AI agents, allowing them to perform complex tasks autonomously, reliably, and with full control. Users can build crews of AI agents using a visual editor, AI copilot, or intuitive APIs, delegating repetitive and time-consuming tasks. The platform provides features for easy building, trusted execution with workflow tracing and agent training, and scalable management with LLM configuration and role-based access control. CrewAI AMP (Agent Management Platform) further streamlines the entire lifecycle from development to production scaling, offering tools for orchestration, integration, observation, optimization, and centralized management.

AI Chat powered by Claude AI is an iOS mobile application designed to be a comprehensive chatbot assistant for daily needs. The app leverages advanced artificial intelligence technologies, including Claude, Gemini, and ChatGPT API, to offer users a wide range of knowledge and support. It aims to empower users by providing quick answers and assistance across various aspects of their lives, making complex information accessible and daily tasks more manageable. This integration of multiple leading AI models ensures a robust and versatile conversational experience, catering to diverse user queries and requirements.

Visus empowers users to create custom ChatGPT AI instances trained specifically on their own documents and knowledge base. This eliminates the need to search through countless documents, as users can simply ask Visus and receive instant, verified answers. The platform is designed to understand natural language, offer limitless knowledge storage, and provide conversational interactions with follow-up questions. Visus emphasizes security with AES 256 encryption and strict permissions enforcement, actively working towards SOC 2 compliance. It integrates with popular tools like Google Drive, Confluence, Notion, Slack, and Microsoft Teams, and offers a Chrome Extension for ubiquitous access. Visus offers various pricing tiers, including a free plan, to cater to individuals and businesses.

Coxwave Align is an analytics engine specifically designed for Gen-AI products, enabling modern organizations to easily analyze and evaluate data from LLM-based conversational products. It provides a comprehensive solution to monitor user interactions with AI chatbots, analyze these interactions to identify areas for improvement, and evaluate chatbot performance to reduce hallucinations and enhance overall quality. The platform offers real-time data saving through pre-built SDKs, a diverse search toolkit for identifying high-priority data, and the ability to analyze data at scale by deep-diving into cohorts. It transforms analysis into auto-generated action items and allows for post-upgrade evaluation of AI chatbots. Coxwave Align offers both a cloud solution for quick setup and an enterprise on-premise solution for full data control and stringent security requirements, being SOC 2 and GDPR compliant.

Agentic Project Management (APM) is an open-source framework designed to manage complex software projects using a team of AI agents. Unlike single-chat approaches, APM coordinates specialized agents for planning, managing, and executing tasks, each operating within its own context. This prevents context degradation and improves consistency. Agents accumulate working context across assignments, and when context limits are reached, a structured 'Handoff' transfers knowledge to a fresh instance. The framework supports user mediation at every step, allowing for visibility and audibility of the workflow. APM integrates with various AI assistants like Claude Code, Cursor, GitHub Copilot, and Gemini CLI, and offers a CLI for easy installation and management. It also includes an 'APM Auto' adaptation for autonomous subagent dispatch for faster prototyping.

langgraph4j is a Java library designed for developing sophisticated AI agentic architectures. It allows developers to build stateful, multi-agent applications that leverage Large Language Models (LLMs). Inspired by the Python library LangGraph, it offers seamless integration with popular Java LLM frameworks like Langchain4j and Spring AI. Key features include stateful execution for managing shared state across graph nodes, support for cyclical graphs essential for agent-based architectures, and explicit control flow definition. The library also provides modularity for building complex systems from reusable components, flexibility for integrating various LLM providers, and robust observability and debugging tools like checkpoints and graph visualization.

GPTeam is an open-source multi-agent simulation platform designed to explore the capabilities of GPT models in fostering multi-agent collaboration and communication. It leverages GPT-4 to create individual agents, each equipped with memory, that interact with one another to achieve predefined goals. Agents move around a simulated world, perform tasks in various locations, and communicate to collaborate on common objectives. The platform's architecture, including agent memory and reflection, is inspired by recent research. Users can observe agent interactions, customize the world by modifying agents or locations via a config file, and integrate with services like Discord, Anthropic Claude, and Window. It offers options to run simulations with different LLMs for cost efficiency.

Uplabs AI provides AI Employees to automate business processes across sales, support, and operations. Their platform offers conversational AI agents for both voice and text interactions, handling tasks like lead qualification, 24/7 multilingual customer support, payment reminders, and satisfaction surveys. Businesses can leverage Uplabs AI for detailed business analysis, AI implementation, and a management platform to control their AI workforce. Key features include real-time dashboards, no-code setup, white-label options, and specialized solutions for industries like banking, insurance, healthcare, real estate, and e-commerce. The tool aims to reduce costs, scale operations, and enable data-driven decisions by transforming conversations into actionable insights.

AI Assist by airfocus is an AI-powered assistant specifically built for product managers, integrated into the airfocus modular product management platform. It provides powerful prompts directly within airfocus item descriptions and comments, enabling users to quickly generate ideas or first drafts, analyze feedback sentiment, simplify complex technical jargon, and obtain brief summaries. The tool aims to significantly increase productivity and save valuable time by automating repetitive tasks and overcoming writer's block. Key features include prompts for writing PRDs, user stories, making text non-technical, showing value, analyzing sentiment, and summarizing long texts, all accessible via simple slash commands.

ChatGPT for Siri is a shortcut that allows users to activate ChatGPT using Siri voice commands on their Apple devices. This integration enables hands-free interaction with ChatGPT, allowing users to ask questions, receive answers, and even save the responses to Apple Notes. The shortcut prompts for a question, sends it to the ChatGPT API, reads the answer aloud, and then offers the option to save the full text to a new note. This is particularly useful for on-the-go use, transforming how users interact with AI by making it more intuitive and efficient. To set up, users need to obtain a ChatGPT API key and input it into the shortcut, which requires a paid subscription to the ChatGPT API as of April 2023.

Task Solving with Langchain Provided Tools as Functions is a powerful framework that allows developers to leverage Langchain tools directly within the AutoGen multi-agent system. This integration facilitates the creation of sophisticated AI applications capable of autonomous task execution and complex problem-solving. By providing a structured way to incorporate Langchain's diverse set of tools, it significantly enhances the capabilities of AutoGen agents, enabling them to interact with external systems, perform data operations, and execute code. This makes it an ideal solution for building collaborative AI projects and developing advanced autonomous agent systems that require robust tool-use functionalities.

Prosper AI offers AI voice agents specifically designed for the healthcare industry, automating patient access and revenue cycle management (RCM) calls. The platform handles tasks such as appointment scheduling, benefit verification, prior authorization initiation and follow-up, claim status checks, and patient billing inquiries. By offloading high-volume, routine phone tasks, Prosper AI helps healthcare organizations reduce administrative costs, improve patient access, and free up staff to focus on higher-value care. The voice agents are built on battle-tested Blueprints™ and integrate with existing PMS and EHR systems, promising quick deployment within weeks. Key benefits include resolving a significant percentage of calls end-to-end, providing 24/7 coverage, and reducing operational costs.

ProMindGPT offers a collection of personalized AI agents designed to assist with various professional tasks. Users can generate diverse content, including tweets, blog posts, LinkedIn posts, and YouTube scripts, utilizing advanced OpenAI GPT-3 and GPT-4 models. Beyond content creation, the platform also provides powerful tools for code assistance, allowing users to fix errors and generate code efficiently. This comprehensive AI solution aims to streamline workflows and save time for professionals across different industries, from content creators to developers, by offering tailored AI 'minds' for specific needs.

skills is an open-source repository by GudaStudio, offering a collection of Agent Skills designed to enhance the capabilities of large language models like Claude. These modular extensions allow Claude to load specialized domain knowledge and workflows on demand, facilitating seamless collaboration with other AI models and tools such as OpenAI Codex and Google Gemini. The project includes skills for delegating coding tasks, enabling prototyping, debugging, and code review. It provides easy installation scripts for Linux/macOS and Windows (PowerShell), supporting user-level, project-level, or custom path installations. The repository also offers recommended global prompts to optimize interaction and state management, asynchronous operations, and a structured workflow for multi-model collaboration, context retrieval, analysis, and code implementation.

awesome-n8n-templates is the largest open-source collection of n8n automation templates, offering over 280 free, ready-to-import workflows. These templates cover a wide range of applications, including Gmail and email automation, Telegram bots, Google Drive and Sheets integration, WordPress, PDF processing, Discord, and OpenAI/LLM integrations. Users can easily download JSON template files and import them into their n8n instance to automate tasks such as AI-powered email labeling, chatbot development, document analysis, and social media management. The collection is continuously updated and supports various AI models like OpenAI GPT-4, Anthropic Claude, and Google Gemini, making it a versatile resource for anyone looking to enhance their automation capabilities with n8n.

GiGOS offers a free, user-friendly platform for comparing and testing various leading AI models in real-time. Users can battle and evaluate models such as Claude 4.5 Sonnet, GPT-5, Gemini 2.5 Flash, Grok 4, Llama 4 Maverick, and DeepSeek R1 side-by-side. The tool is designed to help users understand the differences in performance and capabilities across these advanced AI models. With its intuitive interface, GiGOS simplifies the process of experimenting with different AI outputs, making it an ideal playground for anyone looking to benchmark or explore the strengths of each model for specific tasks.

Youmio empowers users to create, customize, and interact with AI-powered Mio characters. This platform is designed to offer a world of endless possibilities and personalized experiences, allowing users to engage with AI companions in unique ways. While the current description mentions onchain AI agents and a Layer 1 blockchain, the live website content focuses on the character companion aspect, suggesting a shift or a specific product within a larger ecosystem. The tool aims to provide an interactive and customizable AI experience for its users.

Rube by Composio is a universal MCP (Multi-Channel Platform) designed to empower AI chat to interact seamlessly across a multitude of applications. This tool allows users to connect their AI to various services, enabling automation of diverse tasks. For instance, Rube can be used to send emails with Gmail, summarize daily emails, block deep work time, catch up on Slack, draft and post tweets, and create tasks from the latest emails. It integrates with popular platforms such as VSCode, Claude, Cursor, WhatsApp, OpenAI, and N8N, making it a versatile solution for enhancing productivity and workflow automation. However, Rube is being discontinued on May 15, 2026, with full refunds for paying users.