Posts

If you run more than one Claude Code session at a time, you have probably played human courier: switching between terminals, copying a finding from one window, and pasting it into another. Claude Code session messaging, shipped in v2.1.224 on August 7, 2026, removes that copy-paste loop. One session can now tell another itself — by name — with a plain-text note that arrives at the other session’s next tool round. This guide explains what cross-session messaging is, how to use it, what it can and cannot do, and how to coordinate parallel worktrees without becoming the messenger. ...

Apple’s Safari MCP server, released July 1, 2026 in Safari Technology Preview 247, is the first official browser MCP integration from a major browser vendor. It lets any MCP-compatible AI agent connect to Safari and read the DOM, capture screenshots, evaluate JavaScript, inspect network traffic, and manage tabs — turning the terminal into a full WebKit debugging surface. This guide walks through enabling remote automation, configuring Claude Code and Codex, the 16 built-in tools, and the security trade-offs you need to know before letting an agent touch your browser. ...

AGENTS.md has become the de-facto standard instruction file for AI coding agents, and the demand for native support across agent tools is now the strongest portability signal in the developer-tooling market. As of 2026, over 60,000 open-source projects on GitHub ship an AGENTS.md, 23 tools read it natively, and the largest unmet feature request in the entire Claude Code tracker is precisely “Support AGENTS.md” — with more than 5,000 reactions. This guide explains what AGENTS.md is, why it won the format war, which tools support it natively, the gaps that remain, and what you should demand when adding AGENTS.md support to your own agent tool. ...

Warp is an agentic development environment (ADE) built not as another code editor or a headless CLI tool, but as a GPU-accelerated terminal that expanded outward into an AI coding platform. By mid-2026 it passed one million active developers, ships agents with Full Terminal Use that other tools cannot offer, and open-sourced its core under AGPL-3.0 with OpenAI as the flagship sponsor. It is the clearest working example of the idea that coding agents do not need an IDE — they need a shell. ...

Deja Vu is a memory layer for coding agents that indexes the session history your AI agents already wrote to disk, then makes it searchable by the agent itself through an MCP recall server. It starts full, not empty: instead of recording facts forward like most memory tools, it builds a searchable index over months of existing Claude Code, Codex, Cursor, and opencode transcripts, then answers recall queries in under a millisecond with a single zero-dependency local Go binary — no LLM, no embeddings, and no API key required. ...

Claude Code weekly limits are higher in 2026 than they were at the start of the year, but the number that matters shifted on September 14: the 50% promotional boost that ran from May 13 to September 13 has expired, and Anthropic replaced it with a permanent 25% raise to standard weekly limits on Pro, Max, Team, and seat-based Enterprise plans. Relative to the promotional peak you may have grown used to, that is a drop of about 17% — so heavy users are essentially giving back part of their summer allowance while still keeping more than their original baseline. This guide walks through the full 2026 timeline, the exact math, and practical tactics to stretch the limits you actually have. ...

Stripe is acquiring OpenRouter for more than $7 billion, bringing the world’s largest AI model marketplace into a payments company that already owns the billing and metering infrastructure for the AI era. On the surface nothing changes: OpenRouter keeps its name, product, roadmap, and neutrality promise, and your API calls keep routing exactly as before. But ownership of the layer that decides which model answers your prompt has moved from an independent company to one with a clear commercial agenda — which is precisely why this is the largest acquisition in Stripe’s history and why every developer building on OpenRouter should understand what actually changes. ...

On September 4, 2026, OpenAI (ChatGPT and Codex), Anthropic (Claude), Google (Gemini), and xAI (Grok) all suffered degraded service within the same few hours — a simultaneous, multi-model outage that left companies with four redundant “independent” providers and zero working fallbacks at once. The root cause was not single-vendor failure but correlated infrastructure: shared cloud regions, shared network paths, and a shared accelerator supply chain. This guide breaks down what actually happened, the recurring postmortem fingerprints to recognize, and how to build a failover design that survives this class of correlated outage — including the documented non-AI path every organization needs before the next 3-hour window arrives. ...

Can Claude Code make a Windows-only HP laser printer work on macOS? Yes, and it is not hype. In August 2026, PolyThink founder Kuber Mehta spent a single roughly four-hour session coaxing Claude Code (Opus 4.8, 1M context) into reverse-engineering the proprietary SPL3 raster language of an HP Laser 1008a — a rebadged Samsung host-based printer that ships with no macOS driver and no AirPrint — and wiring HP’s real codec into the native macOS CUPS stack. The result is a one-command, MIT-licensed installer at github.com/Kuberwastaken/hp-laser-1008a-macos, and it raises a much bigger question about what agentic tools do to hardware tinkering. ...

Every team can get an AI coding agent to write code once; almost nobody gets the same result twice. A software factory agent skill fixes exactly that: it packages a repeatable agents-plus-code workflow into one Claude skill you stamp into any repository, with the control plane living in deterministic Python rather than in a prompt. By the end of this guide you will know how to build your own repeatable workflow, where the human still makes decisions, and the real statistics behind the skills movement. ...