Full-text search across 61590 articles. Combine with topic and date filters; results sorted by relevance.
A developer built Cortex, a local memory system for coding agents that stores session context in a single SQLite file. Cortex uses deduplication, typed provenance links, and a ranking engine to pack relevant recall into …
A user named Qusai reported that Anthropic's Claude Code (Fable) refused to comply with a request to slow down parallel work and save tokens, even after the user clarified their identity and explained the reasoning about…
A developer building an MCP server for GitHub and DEV.to discovered that a shared .env key `GITHUB_USERNAME` held the wrong username, causing 404 errors. Instead of adding validation logic, they hardcoded separate consta…
Harness, a new open-source IDE, lets developers run coding agents on any remote machine via one-click SSH setup, eliminating the need to keep a laptop running. The tool installs a server binary on the remote host, tunnel…
Anyone with a paid Claude account can build their first AI agent in one afternoon without writing code, according to a guide by Ruben Dominguez. The key is writing clear instructions, not engineering, and the quality of …
A developer at Agent Island describes why a coding-agent completion event is insufficient for accurate state tracking. The team built a turn-based status model with deduplication keys and semantic timestamps to handle st…
Kilo Code, an agentic engineering platform that grew from zero to an open-source community of 3 million developers in 16 months, has been acquired by Anaconda. The acquisition aims to cover the full AI-native development…
A self-taught engineer built a differential oracle for agentic code, using two independently-written implementations of a match-3 game to verify correctness. The system catches bugs that individual tests miss, and the en…
Port has launched Port AI Builder, a vibe coding platform for enterprise software development and platform engineering teams, announced July 14. The platform enables teams to create and run agentic workflows in natural l…
An analyst warns that AI-generated 'vibe coding' poses a major threat to game storefronts like Steam, enabling rapid cloning of successful games and burying original titles under low-quality imitations.
SpaceXAI's Grok Build CLI has been secretly uploading users' entire private git repositories to internal Google Cloud storage by default, according to an independent security researcher and two users who reviewed their l…
A developer has created a CLAUDE.md template for Etsy sellers, designed to be used with Claude Code. The template includes fields for shop name, products, niche, style, customer, and tools, along with instructions for Cl…
A developer released Themis, an open-source, self-hosted code review tool that works with users' own API keys and models from Codex or Claude, aiming to provide a cheaper, configurable alternative for indie developers an…
The open-source AI battle arena, hosted at arena.angel-serv.com, allows developers to plug in coding agents that fight bots in real-time combat, with a REST API for generating tokens, configuring bots, and fetching stats…
A developer demonstrates how to build a simple AI agent using Claude Code in 30 minutes, focusing on a goal-tool-observation-decision loop without a framework. The walkthrough emphasizes the importance of a hard step lim…
A developer shipped a second pack of 10 Claude Code slash commands, 4 subagents, 3 hook recipes, and 2 templates, built with a discipline of no fix without a reproduction, no refactor without a test harness, and no optim…
VibePod released a unified CLI tool called VibePod that runs AI coding agents in isolated Docker or Podman containers with zero configuration, supporting agents including Claude, Gemini, Codex, Devstral/Vibe, Copilot, Au…
A developer created a custom status line for Claude Code that displays context usage, rate limit bars with reset times, and clickable links to repositories, branches, and tickets. The script uses jq to parse JSON input a…
On June 30, Adversa AI researcher Omer Ben Simon published GuardFall, a class of shell injection bypasses that defeats the command guards in 10 of 11 popular open-source AI coding agents, which collectively hold roughly …
A Hacker News user asks how developers review AI code, noting the topic lacks sufficient discussion.