Tencent's Hy4 Preview, an open-source Mixture-of-Experts model with 770B total parameters and 49B active per token, is now available on Vercel's AI Gateway, supporting a 1M-token context window for lo…
Since June 2025, frontier AI labs have withdrawn or restricted model access affecting named coding tools or peer labs four times, according to a ledger compiled by an unnamed source. The instances inc…
Nvidia CEO Jensen Huang said that for a vast array of specific, high-level tasks, Nvidia's ecosystem has already reached AGI-level capability, arguing that the term AGI lacks scientific rigor and has …
On August 5, Anthropic shipped inference hooks for Claude Enterprise, a pre-inference security checkpoint that intercepts every governed prompt before Claude processes it, allowing enterprises to bloc…
Opslane, an open-source LLM agent, uses session recordings and MCP integration to identify and fix bugs that generate no error logs, such as erratic dropdown behavior in onboarding flows. The tool, de…
IQ Routing, a new AI gateway, claims to cut LLM call costs by 40 to 80 percent by routing each request to the cheapest model that meets a quality bar, with a five-step LangChain loop example dropping …
A pilot double-blind evaluation of two LLM agents found that the coding-focused model outperformed a general-purpose model on algorithmic correctness by 18%, but scored lower on readability, while the…
A clash between Claude Code's system-message injection and Qwen3.8's chat template causes a 500 error when using the unsloth/Qwen3.8–27B-GGUF model via Ollama, with the failure occurring in under 300 …
Io.github.smigolsmigol/llmkit v0.4.10, an AI cost tracking tool for spend, budgets, and Claude Code, Cursor, and Cline costs, was published to the official MCP registry on 2026-08-27 and is distribute…
A developer behind the Kombine project detailed how they shipped an iOS version of the app using Kotlin Multiplatform with Compose, despite the original roadmap prioritizing Android, backend, and weba…
A developer at Jian AI Lab tested Archify, the top-ranked project on GitHub Trending, through a real architecture-mapping workflow. The tool passed 9 of 9 showcase checks after four validation rounds,…
Open Agent View, an open-source dashboard for coding agents, launched with support for 11+ harnesses including Claude Code, OpenAI Codex, Cursor, GitHub Copilot, OpenCode, Pi, Antigravity, Mistral Vib…
The OWASP Foundation released the Agentic Skills Top 10 (AST10), a list of the 10 most critical security risks in agentic AI skills across major AI agent platforms, including OpenClaw, Claude Code, Cu…
Pixel Agents, an open-source tool by developer pablodelucca, turns AI coding agents running in terminals into animated pixel-art characters in a virtual office, with a VS Code extension and standalone…
A product manager or engineer can use agentic development environments such as Cursor, Claude Code, Lovable, Bolt.new, or v0 to generate a full-stack web interface from a conversational prompt in 45 m…
Cymulate Research Lab disclosed CVE-2026-35603, a privilege escalation vulnerability in AI coding tools including Claude Code, Cursor, Codex CLI, and Gemini CLI. The flaw allows any standard user to p…
A developer's guide argues that AI coding assistants like Codex and Claude Code are most effective when used as agentic tools with Model Context Protocol (MCP) servers, rather than as chatboxes. The a…
A developer has open-sourced Foremerge, a coordination protocol that helps parallel coding agents avoid semantic conflicts that Git cannot detect. The tool allows agents to declare their intents befor…
James Komo released config-drift-checker, an open-source tool that tests coding-agent setups (CLAUDE.md, skills, hooks) against real agent runs to detect when they stop working, citing that Claude Cod…