Local models are trained on tool calling these days, and they can be pretty good at it, too.

My coding agent had 172 tools and got worse at coding ...

The right accessibility testing tools help organisations catch issues early, improve usability, and build products that work ...

AI agents are now taking over repetitive work, identifying issues humans may miss, and helping teams maintain testing speed ...

In Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes your web development and debugging workflow faster and more ...

MCP (Model Context Protocol) is a protocol that allows LLMs to use external tools as their "hands." While it is already widespread in cloud AIs like Claude and Copilot, the combination of "Local LLM × ...

Anthropic has formalized its Claude Code plugin ecosystem with an official, company-managed directory on GitHub — giving the tool's fast-growing developer community a single vetted source for ...

Both allow you to query your NotebookLM notebooks directly from Claude, getting citation-backed answers from Gemini without leaving your workflow. Use this sequence when a Codex SDK agent must ...

VS Code 1.115 introduced a preview Agents app in VS Code Insiders. VS Code 1.116 added persistent debug logs for current and past agent sessions. Both releases expanded how agents work with terminals, ...

A Claude Skill that enables Claude to write and execute any Playwright automation on-the-fly - from simple page tests to complex multi-step flows. Packaged as a Claude Code Plugin for easy ...

OpenAI launched GPT-5.4 Thursday, its first general-purpose model with native computer-use capabilities, alongside financial plugins that connect ChatGPT directly to Microsoft Excel and Google Sheets.