Topic
20 articles found
Entity Graph Retrieval for AI Agents Semantic search is great for finding memories about similar topics. But it's terrible at finding memories about related entities. If the user mentions "Base," you want memories about their wallet, their crypto payments, and their airdrop strategies — even if none
Two Doors, One Gate Onboarding guardrails and power-user friction look like the same problem. They aren't. June 2026 · 7 min · Karl-Heinz Reichel Table of Contents The Setup The Category Error We Already Made Once Two Layers, Not One Document Letting the Data Set the Threshold Accountability Instead
Introduction Managing an Instagram following list can become messy over time. You follow people, some follow you back, some do not, and eventually it becomes difficult to know who is actually mutual. I wanted to build a simple desktop tool that makes this easier without sending user data to an exter
Sleep Consolidation for AI Memory After months of operation, an AI agent's memory store grows to tens of thousands of items. Retrieval slows down. Irrelevant memories crowd out relevant ones. The agent starts "forgetting" recent context because old memories dilute the signal. Humans solve this with
Portable AI on a USB Stick Package an AI agent with bundled Python, Ollama, and memory into a 340MB self-contained package that runs on any x86_64 Linux machine. norax-portable/ ├── norax.sh # Launcher ├── python/ # Standalone venv (252MB) ├── bin/ollama # Ollama binary (42MB) ├── lib/ollama/ # GGML
Most phishing tools still rely on sending your data to the cloud. That means your “security solution” is often just another data collection point. So I built one that doesn’t do that at all. As developers, we constantly trade security for convenience. We trust browsers to auto-fill credentials. But
No necesitas un SaaS de video para poner a dos personas en una llamada. Con un plano de medios administrado (aquí AWS Chime SDK, pero la forma se generaliza), el lado del servidor de una videollamada 1:1 es una reunión, dos tokens de ingreso, y un interruptor de apagado. Este post construye exactame
This article is part of my submission to the H0: Hack the Zero Stack hackathon, in the Monetizable B2B App track. Most "AI apps" treat the model as a stateless add-on: a chat UI tacked onto a CRUD app, calls billed to an API key the developer hopes nobody finds. The database stores the chat history;
The release of React 19 brings exciting new features and patterns, but it also creates immediate friction for development teams working with existing ESLint configurations. Many developers encounter warnings about deprecated or unstable APIs that were once acceptable, particularly around default pro
GPU passthrough gets the attention, but Proxmox only feels reliable when storage, backups, and restores are organized properly.
Frankly, we don’t see gaming-specific features come to the Android core all too often. Recently, ex-journalist and now Google employee Mishaal Rahman offered up a surprisingly detailed preview of a great new feature coming to Android 17. It is called Foldable gaming mode, and what it does is basical
Welcome to Indie App Spotlight. This is a weekly 9to5Mac series where we showcase the latest apps in the indie app world. If you’re a developer and would like your app featured, get in contact. Mirage is a brand new app that brings best-in-class desktop wireless screen sharing to your entire Apple e
🚀 I built a microservice that generates microservices. 🎥 In this video, I walk you through exactly how it works. https://youtu.be/c1FJ5zyjia4 👇 https://youtu.be/sMTpjqpvH-c 👇 SpringBoot #Java #Microservices #EngineeringLeadership #BackendDevelopment #DevProductivity
Building an Autonomous AI Agent: From Zero to Production Most "AI agents" today are thin wrappers around an API call. They take a prompt, send it to GPT-4, and return the response. That's not an agent — that's a proxy. A real agent has persistent memory, autonomous decision-making, tool use, self-mo
Multi-Signal Memory Architecture for AI Agents Most AI agent memory systems use a single retrieval signal: embedding similarity. You embed the query, embed the memories, and return the top-k by cosine similarity. This works for simple cases but fails spectacularly for agents that need to remember co
In the previous article, we built AI Agents that autonomously search our pgvector database. One limitation remained: the tools were hardcoded inside our Python scripts. Only our code could use them. MCP (Model Context Protocol) fixes this. It turns our search functions into a standalone server that
There is a particular moment that hooks every developer on local AI. You type a question into a terminal, hit enter, and watch a coherent answer stream back — with your Wi-Fi off, no API key, no usage meter ticking, nothing leaving your laptop. The model is just there, running on silicon you already
Every time you ask a chatbot to draft an email, something physical happens a long way away. In a windowless shed the size of a cathedral, thousands of processors light up, draw power from the grid, and dump heat into the air or into water. Multiply that by a billion prompts a day, then by a building
In the previous article, we built an MCP server that any LLM client can connect to locally. In this article, we'll deploy it to the cloud — making it accessible from anywhere. Before: localhost:8000 → pgvector (Docker) After: https://your-app.onrender.com/mcp → Supabase (pgvector) Both services are
In this final article, we'll recap what we built across the series, consolidate the design decisions, and point to where to go next. Starting from a blank Python project, we built a complete AI system step by step: 01_setup_db.py pgvector table + extension 02_create_index.py HNSW index (m=16, ef_con
