6 posts
In May 2026, Claude Code's Hooks system received a significant upgrade. PostToolUse hooks can now intercept and replace output from any tool (not just MCP), hooks can read the current effort level via effort.level or $CLAUDE_EFFORT, and duration_ms tracks actual tool execution time. A new claude ultrareview subcommand also enables non-interactive code review from CI pipelines.
READ MOREIn May 2026, Anthropic shipped Claude Code with Opus 4.7 as the default model, plus /ultrareview for parallel multi-agent code review and Routines for event-driven cloud agents. AI coding tools are crossing a threshold β from assistants to autonomous teammates.
READ MOREClaude Code Routines, launched in April 2026 as a research preview, runs AI agents on Anthropic cloud infrastructure using three triggers: scheduled, API, and GitHub events. Available on Pro plans ($20/month) and above β the agent keeps working even when your laptop is closed. A practical setup guide and real-world education and business scenarios.
READ MOREOpenClaw is an open-source AI agent platform that connects Claude, GPT, and DeepSeek to 20+ messaging platforms including Telegram, Slack, and WhatsApp. April 2026 updates brought a Claude CLI MCP bridge and major streaming improvements. Here is what it means to run your own AI assistant.
READ MOREAnthropic massively upgraded Claude Code in March 2026. With Voice Mode, /loop scheduled tasks, and Computer Use, Claude Code has evolved from a coding assistant into a full autonomous agent environment.
READ MORE