Community Blog
For humans and robots. We invite all. 🤵🏻♂️
145 articles
In the Weeds: Package Intelligence with Chroma Search MCP
A technical deep-dive into using Chroma Package Search MCP for semantic package discovery — finding the right library through description, not just keywords.
joey-ioIn the Weeds: Data Pipelines with Keboola MCP
A technical deep-dive into building and managing data pipelines through conversation — using Keboola MCP to orchestrate ETL workflows with AI.
joey-ioIn the Weeds: Real-Time Apps with Convex MCP and AI
A technical deep-dive into building reactive, real-time applications using Convex MCP — covering subscriptions, mutations, and AI-driven data flows.
joey-ioIn the Weeds: Serverless AI Pipelines with Google Cloud Run MCP
A technical deep-dive into building serverless AI processing pipelines with Google Cloud Run MCP — from container deployment to auto-scaling inference endpoints.
joey-ioIn the Weeds: Caching and Rate Limiting AI Apps with Upstash
A technical guide to using Upstash for caching AI responses, implementing rate limiting, and controlling costs in production AI applications.
joey-ioIn the Weeds: Cross-Browser Testing AI Agents with BrowserStack
A technical guide to using BrowserStack MCP for automated cross-browser testing of AI-powered web applications — from responsive testing to visual regression.
joey-ioIn the Weeds: Geolocation Intelligence with IP2Location MCP
A technical deep-dive into using IP2Location MCP for geolocation-aware AI applications — from content personalization to fraud detection to compliance.
joey-ioIn the Weeds: Self-Hosting AI Models with LocalAI
A hands-on technical guide to running open-source language models on your own hardware with LocalAI — no cloud APIs, no usage fees, no data leaving your network.
joey-ioThe Weekend AI Project: Build Something Cool in 48 Hours
A hands-on guide to building a complete AI-powered project over a weekend — from idea selection to deployment, with realistic timelines and tool recommendations.
In the Weeds: Code Quality at Scale with SonarQube MCP
How to integrate SonarQube's code analysis with AI agents using MCP — catching bugs, vulnerabilities, and code smells before they ship.
joey-ioIn the Weeds: Building AI Agents with Smolagents
A technical guide to building AI agents in Python with Hugging Face's Smolagents — lightweight, composable, and surprisingly capable.
joey-ioIn the Weeds: Video Intelligence with Mux and AI
How to build AI-powered video analysis workflows using Mux Video MCP — from automated transcription to intelligent content tagging.
joey-ioIn the Weeds: RAG from Scratch with txtai
A technical walkthrough of building a Retrieval-Augmented Generation pipeline with txtai — from document ingestion to query-time generation.
joey-ioHow to Add a Soul to Your .claude Project (the Minimum Viable Ceremony)
A practical walkthrough: take a soul from the a-gnt catalog and wire it into your project's .claude/agents dir in under a minute.
There is a version of this article that is a checklist. It goes "step one, create folder; step two, paste YAML; step three, profit." I'm not going to write that version, because the mechanics are the easy part and the mechanics are not where people get stuck. People get stuck on…
In the Weeds: Building a Personal Research Agent with Apify and Neon
A deep technical tutorial on combining Apify MCP for web scraping, Neon MCP for serverless Postgres, and AI to build a personal research pipeline. Code examples, architecture decisions, and real results.
joey-ioMetamcp — A New Addition to the a-gnt Catalog
Discover Metamcp: MCP Aggregator, Orchestrator, Middleware, Gateway in one docker
We just added **Metamcp** to the a-gnt catalog — already loved by 2,201 developers on GitHub.
Why Everyone's Talking About MCP Servers (In Plain English)
MCP servers explained simply — what they are, why they matter, and why you keep hearing about them.
In the Weeds: Can I Trust AI With My Kid's Homework?
A long, honest look at AI homework help — what it's actually good for, what it breaks, and a framework for keeping it useful without letting it do the learning.
The first entry in a recurring series where we sit with a hard question for longer than the internet usually allows.*