Best of ai-agents — June 2025

  1. 1
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·48w

    9 MCP Projects for AI Engineers

    A comprehensive collection of 9 Model Control Protocol (MCP) projects designed for AI engineers, covering various applications from local MCP clients and agentic RAG systems to voice agents and synthetic data generators. The projects demonstrate how to integrate MCP with popular tools like Claude Desktop and Cursor IDE, enabling developers to build more sophisticated AI applications with enhanced tool connectivity and context sharing capabilities.

  2. 2
    Article
    Avatar of medium_jsMedium·47w

    How to Build Production Ready AI Agents in 5 Steps

    A comprehensive 5-step guide for building production-ready AI agents, covering Python foundations with FastAPI and async programming, implementing robust testing and logging, mastering RAG for knowledge retrieval, designing scalable agent architectures with frameworks like LangGraph, and establishing continuous monitoring and improvement processes. The guide emphasizes moving beyond prototype demos to create reliable, maintainable systems that can handle real-world production environments.

  3. 3
    Video
    Avatar of youtubeYouTube·50w

    Build & Sell n8n AI Agents (8+ Hour Course, No Code)

    A comprehensive 8+ hour course teaching beginners how to build and monetize AI agents using n8n, a visual no-code automation platform. The course covers setting up n8n, understanding the difference between AI workflows and AI agents, connecting to APIs like OpenAI, working with data types and JSON, and building practical automations. The instructor claims to have generated over $500,000 in revenue through AI agent development and provides step-by-step guidance for creating 15+ AI automations during the free trial period.

  4. 4
    Article
    Avatar of tdsTowards Data Science·49w

    How to Design My First AI Agent

    A comprehensive guide to designing AI agents covering model selection, tooling choices, and reliability strategies. Explores different LLM options including OpenAI GPT-4, DeepSeek, Claude, and Mistral, each suited for specific use cases. Discusses infrastructure considerations, frameworks like LangGraph and Pydantic-AI, and security aspects. Emphasizes the importance of structured prompting techniques like Chain-of-Thought and ReAct, output validation, and failure handling to build reliable production-ready agents.

  5. 5
    Article
    Avatar of communityCommunity Picks·46w

    n8n-io/self-hosted-ai-starter-kit: The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secur

    An open-source Docker Compose template that sets up a complete local AI development environment combining n8n workflow automation, Ollama for local LLMs, Qdrant vector database, and PostgreSQL. The kit enables developers to build AI agents, document analysis tools, and chatbots while keeping data private and secure on their own infrastructure.

  6. 6
    Article
    Avatar of bytebytegoByteByteGo·46w

    EP169: RAG vs Agentic RAG

    RAG (Retrieval Augmented Generation) combines information retrieval with large language models, but traditional RAG has limitations in adaptability and real-time processing. Agentic RAG introduces AI agents that make decisions, select tools, and refine queries for more accurate responses. The comparison covers Kubernetes fundamentals including control planes, nodes, and key resources like Pods and Deployments. Six space-efficient data structures are highlighted: Bloom Filter, HyperLogLog, Cuckoo Filter, Minhash, SkipList, and Count-Min Sketch. Database normalization forms from 1NF to 4NF are explained for eliminating redundancy and enforcing data integrity.

  7. 7
    Article
    Avatar of langchainLangChain·46w

    The rise of "context engineering"

    Context engineering is emerging as a critical skill for AI engineers, focusing on building dynamic systems that provide LLMs with the right information, tools, and formatting to accomplish tasks reliably. Unlike traditional prompt engineering, context engineering emphasizes providing complete, structured context rather than clever wording. The approach addresses the primary cause of agent failures: inadequate context rather than model limitations. Key components include dynamic information retrieval, appropriate tool selection, proper formatting, and comprehensive system design. LangGraph and LangSmith are positioned as enabling technologies for implementing effective context engineering practices.

  8. 8
    Article
    Avatar of hnHacker News·45w

    The New Skill in AI is Not Prompting, It's Context Engineering

    Context Engineering emerges as a more comprehensive approach than prompt engineering for building effective AI agents. Rather than focusing solely on crafting perfect prompts, it involves designing dynamic systems that provide LLMs with the right information, tools, and format at the right time. The concept encompasses system prompts, user inputs, conversation history, long-term memory, retrieved information (RAG), available tools, and structured outputs. The key difference between basic and sophisticated AI agents lies not in code complexity but in context quality - successful agents gather comprehensive contextual information before generating responses, while failures often stem from inadequate context rather than model limitations.

  9. 9
    Video
    Avatar of youtubeYouTube·46w

    Claude Designer is insane...Ultimate vibe coding UI workflow

    A developer demonstrates how to customize Claude Code into a UI design tool using parallel agents, custom commands, and Git worktrees. The workflow involves creating multiple sub-agents that simultaneously generate different UI variations, allowing 10x faster iteration. Key features include claude.md for custom rules, command templates for reusable workflows, and Git worktree for managing multiple development sandboxes. The author also introduces a Cursor extension called SuperDesign that integrates these capabilities into a visual interface for UI experimentation and iteration.

  10. 10
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·47w

    10 MCP, RAG and AI Agents Projects

    A curated collection of 10 advanced AI engineering projects covering MCP-powered applications, RAG systems, and AI agents. Projects include video RAG with exact timestamp retrieval, corrective RAG with self-assessment, multi-agent flight booking systems, voice-enabled RAG agents, and local alternatives to ChatGPT's research features. The repository contains 70+ hands-on tutorials focusing on real-world implementations of LLMs, memory-enabled agents, multimodal document processing, and performance optimization techniques like binary quantization for 40x faster RAG systems.

  11. 11
    Video
    Avatar of youtubeYouTube·48w

    How to INSTANTLY Build An AI Agent Army in n8n with Claude

    Claude 4 Opus can automatically generate complete AI agent systems in n8n using a single prompt. The process creates a master orchestrating agent with specialized subworkflows, each equipped with relevant tools like Slack, ClickUp, and Airtable. By providing business descriptions and tool specifications, users can generate functional JSON workflows in minutes without coding. The system leverages Claude's extended thinking and web search capabilities to create valid, importable workflows with proper tool connections and error handling.

  12. 12
    Video
    Avatar of youtubeYouTube·48w

    Full Stack AI Agent course with inngest and Gemini

    A comprehensive tutorial on building a full-stack AI agent application using Inngest for background workers and Gemini for AI processing. The application features a smart ticketing system with role-based access control, automated ticket assignment based on user skills, and AI-powered ticket analysis. Key components include user authentication with JWT, MongoDB for data storage, email notifications via background workers, and AI agents that automatically categorize tickets, set priorities, generate helpful notes, and assign them to appropriate moderators based on their skills.

  13. 13
    Article
    Avatar of communityCommunity Picks·46w

    eli64s/readme-ai: README file generator, powered by AI.

    ReadmeAI is a Python-based CLI tool that automatically generates comprehensive README files for software projects using AI language models. It supports multiple LLM providers (OpenAI, Anthropic, Google Gemini, Ollama) and offers extensive customization options including header styles, badges, logos, and navigation layouts. The tool analyzes codebases from various platforms (GitHub, GitLab, Bitbucket, local files) and creates structured documentation with project overviews, feature tables, installation guides, and usage instructions. It includes an offline mode for generating READMEs without API calls and supports containerized deployment via Docker.

  14. 14
    Article
    Avatar of itnextITNEXT·45w

    How to Start Your Own MCP Server with n8n

    n8n version 1.88.0+ includes built-in Model Context Protocol (MCP) support, allowing users to expose workflows as AI-usable tools through MCP Server Trigger nodes and connect to other MCP servers via MCP Client Tool nodes. The guide covers setting up MCP endpoints, configuring authentication, exposing tools, and connecting with AI agents, all without requiring additional installations or Docker images.

  15. 15
    Article
    Avatar of neontechNeon·49w

    app.build: An Open-Source AI Agent That Builds Full-Stack Apps

    app.build is an open-source AI agent that automatically builds and deploys full-stack applications with end-to-end testing and automated deployments. The tool can be started with a simple npx command, creates GitHub repositories, and deploys apps with authentication, databases, and hosting infrastructure. The agent uses a divide-and-conquer approach, breaking app creation into smaller tasks with quality checks at each step to ensure working applications.

  16. 16
    Article
    Avatar of heidloffNiklas Heidloff·47w

    Building agentic Applications with Langflow and MCP

    Langflow is an open-source visual tool for building agentic applications using reusable UI components and Python code. The tutorial demonstrates creating an agent that uses watsonx.ai LLM to search news and generate charts by integrating MCP (Model Context Protocol) tools. It shows how to set up custom components, connect MCP servers for chart generation, and deploy Langflow applications as MCP servers for integration with other agentic systems.

  17. 17
    Video
    Avatar of TechWithTimTech With Tim·48w

    Python Advanced AI Agent Tutorial - LangGraph, LangChain, Tools & More!

    A comprehensive tutorial on building advanced AI agents using LangGraph, LangChain, and Firecrawl. The guide demonstrates creating a coding research assistant that follows structured multi-step workflows to research developer tools and frameworks. It covers both simple agent creation using MCP servers and advanced implementations with custom workflows, structured outputs using Pydantic models, and controlled agent flow through graph-based state management.

  18. 18
    Video
    Avatar of mattpocockMatt Pocock·49w

    Mastra, the AWESOME new TypeScript AI Agent framework

    Mastra is a TypeScript framework for building AI agents that provides syntax for creating agents with instructions and models, automatic memory management, and workflow visualization. It includes a local development environment with chat interface for testing agents before deploying them as REST APIs.

  19. 19
    Article
    Avatar of langchainLangChain·47w

    How and when to build multi-agent systems

    Multi-agent systems require careful consideration of when and how to implement them effectively. Context engineering emerges as the most critical challenge, requiring sophisticated strategies to ensure each agent has appropriate context for their tasks. Systems focused on reading tasks (like research) are generally easier to implement than those emphasizing writing tasks, as read actions are more parallelizable and less prone to conflicting outputs. Production reliability requires durable execution, comprehensive debugging tools, and proper evaluation frameworks. Multi-agent architectures work best for breadth-first queries with high parallelization potential and tasks valuable enough to justify increased token costs.

  20. 20
    Article
    Avatar of huggingfaceHugging Face·49w

    ScreenSuite - The most comprehensive evaluation suite for GUI Agents!

    ScreenSuite is a comprehensive evaluation framework for GUI agents that unifies 13 benchmarks across perception, grounding, single-step actions, and multi-step agent capabilities. The suite evaluates vision language models on their ability to interact with graphical interfaces using only visual input, without accessibility trees or DOM metadata. It includes Dockerized environments for Ubuntu and Android testing, supports both local and remote sandbox execution, and provides standardized evaluation of leading VLMs like Qwen-2.5-VL series, UI-TARS, and GPT-4o on GUI automation tasks.

  21. 21
    Video
    Avatar of aidotengineerAI Engineer·46w

    Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex

    Jerry Liu from LlamaIndex presents a framework for building AI agents that automate knowledge work over unstructured documents. He distinguishes between assistive agents (chat interfaces that help humans get information) and automation agents (background processes that handle routine tasks). The approach requires a comprehensive document toolbox with parsing capabilities for complex PDFs, Excel sheets, and other formats, plus appropriate agent architectures ranging from constrained to unconstrained workflows. Real-world applications include financial due diligence, enterprise search, and technical data sheet processing, with LlamaIndex providing cloud services for document parsing that outperform existing benchmarks.

  22. 22
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·47w

    Deploy any ML model, RAG or Agent as an MCP server

    LitServe now supports MCP (Model Context Protocol) integration through a dedicated endpoint, allowing any ML model, RAG system, or AI agent to be deployed as an MCP server. This eliminates the need for custom integration code for each application. The implementation involves defining input schemas, setup methods, and inference logic in a simple Python class structure. The article also covers a 4-part MCP crash course and demonstrates deploying a Qwen 3 Agentic RAG system using CrewAI, Firecrawl, and LitServe.

  23. 23
    Article
    Avatar of simonwillisonSimon Willison·48w

    Design Patterns for Securing LLM Agents against Prompt Injections

    A comprehensive research paper by 11 authors from IBM, Google, Microsoft and other organizations presents six design patterns to mitigate prompt injection attacks in LLM agents. The patterns include Action-Selector, Plan-Then-Execute, LLM Map-Reduce, Dual LLM, Code-Then-Execute, and Context-Minimization approaches. Each pattern trades some agent flexibility for security by constraining actions and preventing untrusted input from triggering arbitrary tasks. The paper includes ten detailed case studies covering practical applications like SQL agents, email assistants, and customer service chatbots, providing threat models and mitigation strategies for each scenario.

  24. 24
    Video
    Avatar of youtubeYouTube·49w

    How to Build AI Agents in n8n for Beginners! (Full n8n Guide)

    A comprehensive beginner's guide to building AI agents using n8n, covering the fundamentals of workflow automation, the difference between automations and agents, and hands-on tutorials for creating weather reporting agents. The guide walks through setting up triggers, actions, HTTP requests, code nodes, and integrating AI models with tools like OpenAI and Gmail to create dynamic, conversational agents that can perform tasks and access external data sources.

  25. 25
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·49w

    The Full MCP Blueprint—Part 3

    Part 3 of an MCP crash course focuses on building a custom MCP client from scratch, moving beyond prebuilt solutions like Cursor or Claude. It explores the full MCP lifecycle, demonstrates the client-server architecture through practical implementation, and shows how MCP differs from traditional API and function calling approaches. The series addresses the M×N problem in tool integrations and presents MCP as a standardized protocol that enables dynamic tool discovery and invocation at runtime, facilitating plug-and-play interoperability between different AI systems.

See all ai-agents archives