A developer is building an open-source tool to observe and distill Claude Code agents' behavior into a cheaper AI model, effectively creating a backup that eliminates the need for Claude's subscriptio…
Sverklo, a local-first MCP server, launched to give coding agents like Claude Code and Cursor repository memory by tracking symbols, callers, diffs, and git-pinned decisions before edits. The tool, wh…
Researchers at BashControl released a new paper revisiting AI control protocols, comparing resampling strategies from their earlier Ctrl-Z study against retrying protocols similar to those used in Cla…
A developer discovered that the Claude Code status line, typically used only for visual display, contains approximately 30 data fields including session cost, duration, context usage, git branch, mode…
Salesforce Engineering has transitioned from AI-assisted development to fully agentic software creation, with autonomous tools now writing code, reviewing pull requests, and managing deployments acros…
Phoenix Code, the official successor to Adobe's Brackets, launched a new desktop editor that gives AI coding agents visual context of the rendered web page rather than just source code. The editor all…
A developer has created Aweskill, a CLI-first Skill package manager designed to be operated autonomously by AI coding agents. The tool enables agents to install, manage, and troubleshoot their own Ski…
A developer has released "Claude-ITect-Skill," a one-command starter pack that installs 54 skills, 4 agent definitions, and 6 hook files into any project's `.claude/` directory. The tool includes a "c…
A developer's guide to CLAUDE.md files recommends keeping them under 200 lines with only universally applicable rules, as bloated files degrade model accuracy from 95% to 60% based on a 2025 Chroma st…
Linux kernel networking maintainer Paolo Abeni submitted a "significantly bigger" pull request for Linux 7.1-rc5 than typical for this stage of development, attributing the increased patch volume to A…
AISlop, a new open-source command-line tool, now detects "AI code smells" left by coding agents like Claude Code and Cursor, analyzing code for issues such as narrative comments, swallowed exceptions,…
Rig launched a local-first semantic knowledge graph tool that transforms codebases into interactive, navigable maps for AI coding agents. The tool runs entirely on the user's machine with no API keys …
Claude-code-replay reconstructs lost project state from Claude Code session logs by replaying file writes and optionally classifying Bash events through Claude Sonnet 4.6. The tool walks JSONL log fil…
FlashAlpha ships two MCP endpoints with the same 40-tool catalogue but different authentication, and picking the wrong one is the most common setup failure. The claude.ai web client and current Claude…
Anthropic's Claude Code agent suffered a statistically significant five-day performance degradation immediately before the Opus 4.8 model release, with pass rates dropping from a 65% baseline to as lo…
Anthropic has surpassed OpenAI as the most valuable artificial intelligence company, reaching a $900 billion valuation after a $65 billion fund-raising round. The company’s rise was fueled by its Clau…
Harness Engineering introduced a reflection mechanism into the OpenSpec workflow within OpenCode, adding a requirements review step that improved AI-generated code quality. The reflection agent, runni…
A developer used four parallel Claude Code agents to audit 77 personal projects across different stacks and employers in approximately 90 minutes. The multi-agent pattern, which assigns each agent a p…
Headroom, a new macOS menu bar app, reduces Claude Code token usage by approximately 50% by locally trimming prompt bloat and boilerplate before inputs reach the model. The tool processes all data on …
Anthropic released Claude Opus 4.8 on May 22, making the model available simultaneously in Claude Code, the API, and major cloud providers without a waitlist or staged rollout. The new model is roughl…