Best of ai-agents — May 2025

  1. 1
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·50w

    The Full MCP Blueprint

    MCP (Model Context Protocol) provides a standardized way for LLMs to interact with tools and capabilities, solving the M×N integration problem where every tool needs manual connection to every model. The protocol enables dynamic tool discovery, plug-and-play interoperability between systems like Claude and Cursor, and transforms AI development from prompt engineering to systems engineering. MCP uses a Host-Client-Server architecture with JSON-RPC communication and supports various transport mechanisms including Stdio and HTTP.

  2. 2
    Article
    Avatar of phProduct Hunt·1y

    VoltAgent - Build TS AI agents with n8n-style observability

    VoltAgent is an open-source TypeScript framework designed to build and orchestrate AI agents with enhanced observability features similar to n8n. It provides developers with flexibility through code-based customization while offering a visual console for debugging and monitoring agent executions. Key features include memory management, multi-agent orchestration, and an LLM-agnostic architecture, making it a versatile tool for developers seeking deeper control and insights into AI workflows.

  3. 3
    Video
    Avatar of thecodingslothThe Coding Sloth·51w

    Everything You Need To Know About AI Agents

    AI agents, distinct from typical LLMs, are systems that reason, plan, and execute tasks autonomously using a loop-based workflow. They utilize tools like APIs, databases, and systems interaction to enhance functionality. These agents can be structured in various ways, including single agents, multi-agent crews, hierarchical systems, and hybrid models, to perform tasks efficiently. The post provides insights into building AI agents and explores the potential applications and tools available to create them.

  4. 4
    Video
    Avatar of youtubeYouTube·50w

    From Zero to Your First AI Agent in 25 Minutes (No Coding)

    AI agents are autonomous systems that can reason, plan, and take actions using three core components: a brain (LLM), memory for context retention, and tools for external interactions. Unlike static automations that follow predefined steps, agents dynamically adapt and make decisions. The tutorial demonstrates building a practical trail running assistant using N8N's visual interface, connecting Google Calendar, weather APIs, Gmail, and custom HTTP requests without any coding. The agent checks schedules, analyzes weather conditions, recommends appropriate trails from a personal database, and sends customized email notifications.

  5. 5
    Video
    Avatar of bytegradByteGrad·50w

    Build Next.js MCP - Your Website & MCP-Server In 1 App!

    A comprehensive tutorial demonstrating how to build a Next.js application that includes both a traditional website and an MCP (Model Context Protocol) server in a single app. The guide covers creating MCP tools that AI agents can invoke, implementing course recommendation functionality based on user experience level, deploying to Vercel with Redis integration, and testing the MCP server with GitHub Copilot. The tutorial also showcases CodeRabbit for automated code reviews and includes practical examples of AI agent interactions with custom MCP endpoints.

  6. 6
    Article
    Avatar of confConfluent Blog·1y

    How to build a multi-agent orchestrator using Flink and Kafka

    The post explores the creation of multi-agent systems using an orchestrator pattern, with Apache Flink and Kafka as key technologies. It highlights the necessity of dividing complex tasks among specialized AI agents for better collaboration and problem-solving. The orchestrator facilitates efficient message routing and real-time decision-making by interpreting and distributing tasks dynamically. The combination of Flink's real-time processing and Kafka's event-driven messaging creates a scalable, adaptable system without rigid dependencies.

  7. 7
    Article
    Avatar of freecodecampfreeCodeCamp·1y

    How to Create Serverless AI Agents with Langbase Docs MCP Server in Minutes

    Learn to set up the Langbase Docs MCP server within the Cursor AI code editor to create serverless AI agents quickly. This tutorial guides you through using Langbase SDK, enabling memory-enhanced, agentic AI systems by providing live, on-demand Langbase documentation as context. The integration helps streamline AI model workflows by reducing context switching and allows developers to extend AI capabilities seamlessly.

  8. 8
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·51w

    Build a Multi-agent Network with Agent2Agent Protocol

    Learn how to build a network of AI agents using the Agent2Agent (A2A) protocol, which facilitates communication and collaboration among agents. The tutorial demonstrates how to serve agents locally with specific skills, deploy multiple types of agents, and integrate client-side applications. The post also includes links to further resources and code examples.

  9. 9
    Article
    Avatar of newstackThe New Stack·1y

    A2A, MCP, Kafka and Flink: The New Stack for AI Agents

    The post discusses the need for a new infrastructure stack to enable AI agents to collaborate effectively. This stack includes four open components: Google’s Agent2Agent (A2A) protocol for agent communication, Anthropic’s Model Context Protocol (MCP) for tool access, Apache Kafka for event-driven communication, and Apache Flink for real-time data processing. By integrating these technologies, AI agents can operate beyond isolated silos, scaling to complex ecosystems that facilitate collaboration, observability, and resilience.

  10. 10
    Video
    Avatar of youtubeYouTube·52w

    Building AI Agents In 44 Minutes

    The post explores how to build AI agents using various frameworks and tools, catering to both non-coding beginners and experienced developers. It highlights the importance of understanding AI agent components, agentic workflows, and the nuances of prompt engineering. Practical examples are provided using different tools and models, and the post discusses potential AI agent applications in business and startups. There is mention of recent advancements in voice and image generation and how AI agents can be leveraged for various tasks.

  11. 11
    Article
    Avatar of tdsTowards Data Science·50w

    May Must-Reads: Math for Machine Learning Engineers, LLMs, Agent Protocols, and More

    A monthly roundup of popular machine learning and data science articles covering essential math skills for ML engineers, beginner guides to LLMs and RAG, software engineering concepts like inheritance, agent communication protocols, Model Context Protocol, PyTorch applications, healthcare ML projects, and time series forecasting techniques. The collection also introduces new authors contributing to the data science community.

  12. 12
    Video
    Avatar of microsoftdeveloperMicrosoft Developer·51w

    Use VS Code to build AI apps and agents | BRK117

    The post discusses using VS Code to develop and deploy AI applications and agents with Azure services. It covers creating local AI agents using MCP servers for tool interfacing, employing GitHub Copilot for code generation, and utilizing Azure for scaling and deployment. It highlights the use of the Azure AI toolkit extension for model selection, prompt generation, and the configuration of AI agents. The post also showcases how to integrate Azure Foundry for secure and enterprise-scale AI agent management.

  13. 13
    Article
    Avatar of tdsTowards Data Science·1y

    Agentic AI 101: Starting Your Journey Building AI Agents

    Explore the fundamentals of creating AI agents using large language models (LLMs). The post introduces various tools, including Python packages like Agno, for interacting with models such as Gemini. It covers creating simple agents to more advanced ones with reasoning, tools, memory, and knowledge integration. The guide aims to offer a pathway to develop AI agents efficiently, leveraging APIs and various toolsets for enhanced interaction and automation.

See all ai-agents archives