A developer known as Nekoautomata Miki built PluginProof, a tool that checks npm packages for structural failures that survive basic manifest validation, such as missing files in the tarball, version …
Datopian released PortalJS, an open-source, AI-native framework for building data portals that uses agentic skills to help teams choose an architecture, scaffold it, and load data. The framework ships…
OpenAI CEO Sam Altman signaled the company is prepared to cut prices for its flagship AI models by up to 75%, as competition intensifies with US rival Anthropic and cheaper Chinese alternatives. In a …
A new analysis finds that over 250 AI coding add-ons now exist, but they are catalogued by vendor rather than by task, making it difficult for developers to find the right tool for a specific job. The…
Coding agents that combine models, runtimes like Claude Code, and tools such as file write carry inherent safety risks, including potential data loss or system damage from misaligned model behavior or…
A new browser-based tool lets users browse, search, and analyze their Claude and ChatGPT chat histories entirely locally, with no data uploaded. The tool supports importing data exports from both plat…
AWS has shipped a self-hosted control plane called the Claude apps gateway for AWS that gives organizations a single point of control over access, cost, and policy for Claude Code and Claude Desktop. …
A developer's guide details how to run Anthropic's Claude Code CLI for free using third-party API proxy services AgentRouter and HCNSEC. The guide provides step-by-step instructions for installation, …
A developer built Pinpoint, a macOS menu-bar app that lets users annotate screenshots with numbered markers and structured text, so AI agents like Claude Code and Cursor can precisely identify UI elem…
Agentic coding has shifted the bottleneck from writing code to maintaining it, and AI agents are now being applied to production problem-solving, which accounts for 60% to 70% of developers' work. Spi…
New testing by AI consultancy Systima found that agent harness configuration can significantly inflate token overhead and enterprise AI deployment costs, with research showing that changing the harnes…
Milepost, a free open-source plugin for Claude Code, provides persistent long-term memory by automatically writing a plain-markdown diary of milestones, decisions, and status updates during sessions, …
TormentNexus, an open-source AI control plane with 26,000+ MCP tools, has been released with a one-command install via npx. The local-first system supports 38+ AI coding agents, persistent multi-tier …
A developer building a Blockly-based platform with Claude Code via Telegram encountered a recurring bug where new API endpoints were repeatedly missing from Spring Security's permitAll() list. The mod…
Codex hit 7 million active users on July 13, 2026, a 10x surge from 600,000 at the start of the year, while Claude Code reached $2.5 billion in annualized revenue by February. The divergence between u…
Victor Cortes built VichuFlow, an open-source Go runtime that enforces a separation of responsibilities between coding agents and verification. The project addresses the architectural problem of agent…
A new study from arXiv:2607.12161v1 analyzing 2,848 Claude Code runs across 103 tasks finds that reducing retrieved context or tool output does not reliably lower billed costs for API-based coding age…
Syncless has launched Devices, a feature that lets a single AI agent operate across multiple machines simultaneously in one conversation turn, eliminating the need for SSH tunnels, remote desktops, or…
Harness Engineering built a fully automated coding loop inside OpenCode using DeepSeek-V4-Pro and DeepSeek-V4-Flash, enabling low-cost agentic code iteration. The loop, inspired by Andrew Ng's breakdo…
A developer who ran a persistent personal-AI system on Claude Code for one month found that greater AI capability did not reduce avoidance of actions that could produce rejection, but instead made the…