Norax builds an entity graph from its memory store to improve retrieval for AI agents. The graph uses entity extraction, co-occurrence edges, community detection, and weighted edges to capture relatio…
A developer built an artist attribution system using PyTorch and a pretrained ResNet-50 model. The system classifies paintings by artist with top-3 predictions, leveraging transfer learning for effici…
A developer built a complete RAG system from scratch using pgvector, Gemini embeddings, and MCP, covering setup, indexing, ingestion, search, and multi-step agents. The series concluded with deploymen…
A developer built and deployed a Retrieval-Augmented Generation (RAG) system to the cloud using Render and Supabase. The system uses pgvector for vector search and is accessible via an MCP server host…
AI data centers consumed about 1.5% of global electricity in 2024, projected to reach under 3% by 2030, but local impacts are severe: in Ireland they use 22% of national electricity, and in the US the…
A developer's guide explains how to run open-source AI models locally on consumer hardware in 2026, highlighting that a mid-range laptop can now run models once considered frontier-class. The guide co…
A developer built a reusable tool server using the Model Context Protocol (MCP) to expose pgvector search functions as a standalone server that any LLM client can connect to. The implementation uses F…
Norax developed a multi-signal memory architecture for AI agents that combines exact term matching, dense vector similarity, temporal decay, and entity graph reranking. The system outperforms single-s…
A developer built Norax, a 7th-generation autonomous AI agent with persistent memory, autonomous decision-making, and cost optimization. The agent uses a scratchpad for hot state, semantic/procedural/…
A developer building a RAG system from scratch implemented Tool Use, allowing the LLM to autonomously decide when to call search functions. The approach replaces a hardcoded search-then-answer flow wi…
A developer built a RAG system from scratch using pgvector and Gemini embeddings, explaining design decisions such as choosing pgvector over dedicated vector databases, using 768-dimensional embedding…
A developer built a RAG (Retrieval-Augmented Generation) system from scratch using pgvector and Google Gemini, implementing a full pipeline for embedding, vector storage, and semantic search. The proj…
A developer built a demo showing AI agents that can write their own SKILL.md files, enabling them to reuse learned procedures and cut total effort nearly in half. The Agent Skills open standard, intro…
A developer built a cryptographically verifiable agent behavior system that produces tamper-proof receipts proving an AI agent followed approved rules. The demo uses standard hashing and signatures to…
A developer built token-warden, an open-source plugin for Claude Code that only retains agent memory rules if they can prove they save at least twice the tokens they cost. The tool benchmarks candidat…
A developer breaks down the five essential components of production-grade AI agents: planning, tool use, memory, constraints, and verification. The post argues that agent failures stem from workflow d…
A developer building TTT, a terminal text editor and IDE in Go, created a built-in scripted interaction system that allows AI agents to drive the editor like Playwright drives a browser. The system in…
A developer built an AI agent using active inference that becomes curious on its own by minimizing surprise rather than chasing rewards. On a foraging task, the agent achieved 100% success by checking…
Shridhar Shah, a senior software engineer at Outshift by Cisco, built two AI agents to test theory of mind using the Sally-Anne false-belief test. One agent, which only tracks reality, fails the test …
A developer built a 90-line AI agent that mimics sleep to consolidate memories, achieving 100% recall compared to 75% for an identical agent without sleep. The agent replays daily experiences during a…