Full-text search across 1933 articles. Combine with topic and date filters; results sorted by relevance.
AgentWire, an open-source observability and security layer for AI agent workflows, has been released as a minimal viable product (MVP) built on ASP.NET Core. The tool treats agent traffic like network packets, enabling t…
A new open-source tool called Qarinah reduces LLM coding agent context from over 442k tokens to about 5.6k tokens—a 98% reduction—by treating project knowledge as typed events with explicit relations like supersedes or b…
An engineer argues that tracking only monthly spend and seat counts for LLM agents like Claude Code fails to measure whether developers use the tools effectively, and recommends the open-source local auditing tool cc-aud…
Mahdi, a senior full-stack engineer and international STEM educator, has joined DEV to share architectural patterns, deployment templates, and tested source code. Over eight years, he has built systems including financia…
Anthropic's Claude Code, a terminal-based AI agent, shifts coding workflows by executing file changes directly in the command line rather than requiring copy-paste between a chat window and an IDE. The tool indexes local…
Codeberg e.V., a German nonprofit open-source hosting platform, voted to ban projects related to cryptocurrency and large language models (LLMs), including those created or maintained with heavy LLM use, in a decision th…
A software engineer describes shifting from writing code to reviewing pull requests and using AI tools like Claude to implement features, leading to higher productivity but a loss of craftsmanship. The engineer questions…
A developer attempting to integrate Google Calendar with an AI agent in OpenClaw discovered that OAuth authentication and operational infrastructure are far more complex than expected. The developer found that using a de…
Serverless containers enable ML model deployment from a Jupyter notebook to a live API endpoint in under 10 minutes, bypassing traditional infrastructure management. The approach uses a FastAPI wrapper and a Docker conta…
A developer built a local-first voice-enabled AI assistant by combining Nous Research's open-source Hermes Agent framework with Kokoro TTS, achieving natural speech responses without cloud API costs or data exposure. The…
A new analysis identifies data and concept drift as the primary cause of machine learning model failures after deployment, warning that without rigorous MLOps strategies including automated monitoring and retraining, mod…
ChronoWeave is a system that extracts causal graphs from historical text and lays them out as interactive maps, using a neural network to position causally-connected events close together. The project's spatial intellige…
A new AI workflow called Panopticon automates the maintenance of organizational documentation by using an LLM agent to scan repositories, detect changes, and update documentation without human intervention, creating a se…
A production-ready chatbot requires grounded retrieval, conversational state, and an operational backbone, not just a model, according to a technical guide for developers. The guide recommends starting with repetitive ta…
SigNoz's telemetry profiler reduced span storage by 95%, from 13,404 to 672, while preserving all 31 injected error traces, demonstrating that aggressive sampling of high-volume spans can slash storage costs without losi…
A developer's automated screening system falsely flagged legitimate vendors like Browserbase and Tavily as honeypots because it assumed payment address rotation indicates fraud, highlighting the need for more nuanced ano…
A developer proposes an architecture for AI agents in regulated industries that prioritizes human approval over autonomy, with four layers: document intake, agent work, a mandatory human approval gate, and a detailed aud…
A developer reports that integrating Google's Air Quality MCP (Model Context Protocol) provides longitudinal intelligence rather than just a snapshot, using the `get_air_quality_history` endpoint to analyze 720-hour (30-…
A developer who built CourtGPT.ai to serve 6.7M+ legal records shares 18 months of lessons on production RAG systems. Key findings include that hybrid search (BM25 + vector) achieves 92% recall at top-10, semantic chunki…
A developer built a Node.js support workflow with a deliberately limited AI assistant that may propose replies but cannot send them, enforcing a human approval gate to prevent fluency from being mistaken for authority. T…