Full-text search across 7932 articles. Combine with topic and date filters; results sorted by relevance.
A developer's hands-on testing of MCP servers for Claude Code and Cursor in 2026 found that most fail to meet criteria of working with the July 28 spec update, which made the protocol stateless and not backward compatibl…
Google is joining the Agent Plugins project as a Core Maintainer, represented by Kevin Hou, and will integrate the open, vendor-neutral specification into its products. The Agent Plugins 1.0.0 specification, published by…
Agent Plugins 1.0.0, an open, vendor-neutral standard for plugins that extend AI agents, is now publicly available. The format, initiated by Vercel and refined with AWS, Anysphere, GitHub, Microsoft, and OpenAI, provides…
Nous Research's open-source Hermes Agent, an autonomous AI agent that runs as a persistent daemon and integrates with 20+ messaging platforms, offers a self-improving memory loop and 70 built-in tools, according to a han…
SpaceX's first quarterly earnings as a public company reveal that its core business is telecom and AI compute leasing, not rockets, with Starlink generating $4.2 billion in revenue and the neocloud business driving $15.8…
A 17-year-old developer built VibeCurb, a collection of constraint skill files that force AI coding agents to think about design before writing code. The system uses a four-phase pipeline—design read, quality gate, preci…
Make This Better launched a feedback widget that captures annotated screenshots, console errors, and DOM state, and uses AI triage to turn user reports into tasks for coding agents like Claude Code, Cursor, and Codex. Th…
Developer Siddhartha Katiyar built ContextOS, a local-first context engine that indexes software repositories using Tree-sitter and SQLite FTS5 to improve AI coding assistants' retrieval accuracy. In benchmarks against t…
Cisco Talos reported on August 4 that recovered prompt logs showed threat actors using Claude Code, Codex, Cursor, Gemini and other AI tools for malicious development, fraud and vulnerability work. The researchers found …
Amazon OpenSearch Service now exposes a native Model Context Protocol (MCP) endpoint, allowing AI agents like Claude, Amazon Q, and Cursor to connect directly without custom connectors. The endpoint, part of the ML Commo…
Asif Waliuddin, an engineer, rolled back his fleet of chief-of-staff agents to an older model version after finding the newer model performed worse in real sessions, despite better benchmark scores. Citing Cursor's findi…
Cua, an open-source project for Computer-Use Agents, shipped an update providing infrastructure to train and evaluate AI agents that control full desktops on macOS, Linux, and Windows without stealing focus. The project,…
XCREENER released an open-source MCP server that lets AI agents screen Crypto, Forex, Indices, Commodities, and Metals markets using plain English. The local stdio bridge exposes XQL validate, explain, run, and natural-l…
Claude Code, Anthropic's AI coding agent, frequently fails on multi-file refactors with opaque errors such as 'stream interrupted', often caused by stale file paths, according to a developer's analysis. The developer rec…
Vibrisse, a studio focused on eco-design and performance, warns that unconstrained use of generative AI tools like Cursor, Copilot, and Cline can silently erode a codebase's identity and introduce technical debt. The tea…
A new agent skill enforces ASD-STE100 Simplified Technical English, the controlled language used in aerospace since 1983, to force LLMs to write unambiguous technical documentation. In 96 runs across 6 Claude models and …
OpenAI's GPT-5.6 Sol achieved a 38.3% ARC-AGI-3 score with a harness that retained reasoning and used compaction, up from 13.3%, while cutting output tokens sixfold. The same model helped OpenAI reduce serving costs by 2…
A new State of AI Report from DVC, a venture firm that has tracked the AI market for a decade, reveals five underappreciated truths about the AI economy, including that five-person teams now routinely challenge $100 bill…
Paul Bakaus created Impeccable, a design skill package that runs inside Claude Code, Gemini CLI, Codex CLI, Cursor, and GitHub Copilot to enforce strict aesthetic guardrails for generative coding agents. The tool provide…
Cybersecurity researchers at Tel Aviv University and Intuit have identified a new attack called 'hallusquatting' that exploits AI coding assistants' tendency to hallucinate non-existent software package names, allowing a…