Anthropic has launched background computer use for Claude Code on macOS, available to Pro and Max customers, enabling the AI agent to operate without taking over the user's cursor. The feature follows…
A new open-source Agent Skill, github-readme-generator, enables coding agents to write or refresh a repository's README.md based on actual repository contents, omitting any claim it cannot trace to a …
A developer built Dokpod.io, an AI knowledge vault that uses the Model Context Protocol (MCP) to let AI coding assistants like Cursor and Claude Code query indexed project assets on demand, eliminatin…
CodeYam CEO and cofounder Nadia Eldeib outlined two installation paths for CodeYam: a CodeYam MCPB (Model Context Protocol Bundle) desktop extension for Claude Desktop aimed at newer or non-technical …
A developer's blog post argues that agentic coding systems require a 'human harness' alongside the model harness, defining a harness as a system that enables safe execution through transmission and se…
Google has rebuilt its Conductor tool as a portable plugin that installs into both the Antigravity CLI and Anthropic's Claude Code, marking the first time Google ships first-party tooling for a compet…
NVIDIA released Switchyard, a Rust proxy and library that routes and translates LLM traffic across OpenAI and Anthropic APIs, under Apache 2.0, but labels it pre-alpha and experimental, not for produc…
SandboxAQ's Switch team now operates with five human developers and 45 AI agents collaborating in Slack and Discord, a shift that makes AI agents more than two-thirds of the team. The team built Switc…
OpenCode, an open-source terminal coding agent built by the SST team, has surpassed 180,000 GitHub stars and 7.5 million monthly active developers, overtaking Claude Code in user count within 18 month…
A new engineering paradigm called 'graph engineering' is replacing 'loop engineering' in AI development, according to an essay by The AI Corner. The shift was highlighted when Peter Steinberger, creat…
Francisco Carlos Serra released Agent Voice Kit, an open-source tool that lets users talk to AI agents like Claude Code, pi, Codex, and Gemini CLI locally, with dictation and optional text-to-speech, …
Vestige, a local-first memory layer for AI agents, launches as a 25MB Rust binary over MCP that uses causal and temporal links to trace failures back to their root causes, citing research from Nature …
A developer built Nightshift, a tool that transforms long AI coding sessions into structured 'shifts' with work contracts and run state stored on disk rather than only in conversation. It supports bot…
A developer built Magic Diff, an open-source tool that uses AI to summarize code changes across committed or uncommitted files, aiming to improve the review of AI-generated code. Written in Go/Wails/R…
FrontierHarness Eval, a new benchmark from Runta, tested nine AI coding harnesses on the same model and found median cost per successful task varies by 17x, with Claude Code v2.1.237 passing 19 tasks …
A developer created 'stop-manual-testing', a skill for AI coding agents that requires them to build and run machine-checkable verification criteria before declaring a task complete. The skill aims to …
A developer found that Claude Code's PreToolUse hooks registered on the Read tool do not fire when file contents are accessed via Bash commands like cat, allowing secrets to reach the model. Testing o…
Anthropic removed over 80% of Claude Code's system prompt for Claude Opus 5 and Claude Fable 5 with no loss in coding evaluations, demonstrating that system prompts have a shelf life as models improve…
Aplexica, a new local open-source application, enables cross-agent state portability for AI coding agents, allowing users to switch between agents like Claude Code and Codex without losing memories, s…
A developer's analysis suggests that the economic promise of AI replacing human workers is faltering, citing examples like Klarna rehiring customer service reps and Gartner's forecast that half of com…