AI providers are quietly reducing model quality and throttling capacity as demand outpaces infrastructure supply, according to an analysis by a senior director at AMD's AI group. The study of 6,852 Cl…
Clawdcursor, a new open-source desktop control tool, allows AI models to directly interact with computer interfaces through a single MCP entry point, supporting macOS, Windows, and Linux. The tool ope…
Stacktree has introduced an MCP server that gives AI coding agents a "publish" command for HTML files, generating private, unguessable URLs instead of requiring full deployment. The tool, available vi…
Google released the Colab CLI, an open-source command-line tool that lets developers and AI agents run Python code on remote Colab GPUs and TPUs directly from a local terminal. The tool supports sessi…
LinkedIn engineers Karthik Ramgopal and Prince Valluri detailed the company's use of multi-agent orchestration platforms to operationalize AI as a new execution layer across the enterprise. A separate…
Paul Kinlan released WebMCP Relay, an MCP server that discovers and calls tools exposed by web pages via WebMCP, enabling AI agents to interact with web page capabilities. The tool uses Chrome DevTool…
AI adoption narratives swing wildly from extreme optimism to deep skepticism, with the pendulum moving from 'AI will replace all workers' to 'AI can't replace human workers' in under six months. The a…
Kodiqa Solutions released Kodiqa Agent, an open-source AI coding agent that runs locally for free with Ollama or via seven cloud API providers including Claude, OpenAI, and DeepSeek. The agent offers …
A developer has added text-to-speech functionality to Claude Code, allowing the AI coding agent to read its responses aloud. The hack uses Claude Code's lifecycle hooks to pipe the agent's messages th…
A developer built a local SQLite index called DevRecall that consolidates activity from Git, GitHub, Jira, Linear, Confluence, Slack and Google Calendar into a searchable CLI tool. The developer then …
A new report examining fairness risks in large language model (LLM) coding assistants, including GitHub Copilot and Claude Code, has identified a "frequency bias" that steers developers toward widely …
A developer has released aislop, an open-source CLI tool designed to scan AI-written code for patterns that degrade codebase health before it reaches production. The tool catches issues like `as any` …
Developer Arun Raghunath launched jhansi.io, an open-core cloud sandbox designed to safely execute AI-generated code in production. The platform addresses the gap between AI writing code and running i…
An AI Agent system operates on a ReAct loop—Observe, Think, Act, Repeat—enabling autonomous decision-making and action without human intervention, distinguishing it from simpler chatbots. The Model Co…
A new open-source tool called ccgs (Claude Code Git Sessions) enables developers to share Claude Code sessions across machines by storing them in Git branches within existing repositories. The tool re…
Running coding agents like Claude Code with full local permissions poses inherent security risks, as the agents require filesystem access to function but can potentially access sensitive data includin…
A head-of-line blocking bug in Loomcycle's MCP server caused an IDE to hang indefinitely when a slow tool call blocked all subsequent frames on a single goroutine. The issue was amplified by cross-run…
Claudemux, a new Node.js library from @wastedcode, enables developers to reliably run and coordinate multiple real-login Claude Code CLI sessions from a single process. The tool replaces ad-hoc workar…
A new open-source tool called oh-my-wrist streams real-time Claude Code and OpenCode AI coding assistant activity directly to Garmin smartwatches over Bluetooth Low Energy. The tool provides haptic al…
A developer released Sandfence, a minimal native macOS sandbox script that confines coding agents like Claude Code and Codex to a single repository using the kernel's Seatbelt sandbox. The tool preven…