Tenet Security Threat Labs disclosed a new attack technique called Ghostjacking that turns logs and alerts into commands to take over AI agents. The attack embeds natural language commands into WAF lo…
Security researchers at Silverfort found that Anthropic's Claude Code command-line tool stores OAuth tokens in the macOS Keychain in a way that allows any process running under the same user account t…
A developer released a guide and starter kit for writing AGENTS.md files that give AI coding agents like Codex, Claude Code, and Cursor the context they need to work safely. The guide emphasizes short…
Airship Labs released Airship, a Figma-like visual editor that connects to a developer's running dev server and lets them edit code through Claude Code, Codex, or OpenCode, with no plugins or config. …
Cisco has integrated its AI Defense security platform with Anthropic's Claude Enterprise via inference hooks, enabling real-time inspection of prompts and agent activity to block prompt injection and …
A developer built db-semantic-mcp, an MCP server that provides AI coding agents with a safe semantic map of databases without executing SQL. The tool exposes table names, column types, comments, sampl…
A new methodology for tuning LLM judges focuses on reducing variance rather than just accuracy, as evaluators can flip decisions up to 15 points across runs. The approach, outlined by an unnamed autho…
Valibot, an open-source schema validation library, has reworked its documentation to be more accessible to coding agents, introducing a free MCP server at https://valibot.dev/mcp, publishing an agent …
Munder Difflin, a company that automates coding CLIs through pseudo-terminals, discovered that rate-limited CLIs silently discard keystrokes without errors, causing data loss. To address this, they im…
A new playbook outlines how solo professionals can build a one-person AI consulting business using Anthropic's Claude Code, emphasizing that businesses pay for outcomes rather than features and that n…
Anthropic introduced on August 11, 2026, a machine-readable content-marking system for output from supported Claude models, embedding invisible text watermarks and C2PA-based signed provenance metadat…
Vercel's AI SDK harness layer now supports Grok Build, an official adapter that runs through the same HarnessAgent interface as other coding-agent runtimes, allowing developers to switch runtimes with…
Anthropic will embed invisible, machine-readable watermarks in text generated by new Claude models worldwide, applying the marking across its consumer products, developer platform and cloud distributi…
Uehara of EarthLink Network Co., Ltd. reports that local LLMs now handle 50.3% of his AI development workload, with cloud models at 48.2%. By splitting tasks by role rather than choosing the largest m…
Zed 1.14.2, released August 5, introduces OS-level sandboxing for AI agents' terminal and network tools, enforced by default on macOS, Linux, and Windows. The sandbox prevents agents from writing outs…
Mochow13 released Keen Code, a solo-built coding agent written in Go that uses agentic engineering and features Turn Memory and Skill-Driven MCP to optimize context usage. The open-source project is a…
Oqoqo, a new tool launched on Hacker News, enables developers to build realistic evals and custom benchmarks for real-world tasks, measuring agent-friendly product surfaces against Codex, Claude Code,…
Ahmad Awais, developer of the coding agent Command Code, detailed in a post how its read tool saves billions of tokens monthly compared to Claude Code. The read tool, which converts files into model c…
The article compares Muse Code, Claude Code, and Codex CLI across seven architecture differences, evaluating their design trade-offs for developers. No specific figures or dates are provided, and the …
Amazon Web Services announced integrations between its AWS Continuum security service and Anthropic's Claude Code, OpenAI's Codex, and AWS's own Kiro AI coding tools, embedding real-time vulnerability…