Anthropic Just Took GitHub’s #1 Spot With Its Own Repo — Dev Trends, Week of May 6–12
This week’s GitHub trending #1 was Anthropic’s own financial-services repo — 13K stars in 7 days. The theme: where and how do we run AI agents?
This week’s GitHub trending #1 was Anthropic’s own financial-services repo — 13K stars in 7 days. The theme: where and how do we run AI agents?
Anthropic launched Claude for Legal with 20+ MCP connectors and 12 practice plugins. Google embedded Gemini Intelligence into Android, and GPT-5.5 Instant became ChatGPT’s default.
After 2 months running 12 projects, 30 slash commands, and 40 launchd jobs on Claude Code, here are the 5 techniques that actually moved the needle.
VS Code 1.118 silently injected a Copilot co-author trailer into commits — rolled back in 1.119. Plus a Linux RAT hunting DevOps creds and the largest Canvas LMS breach to date.
Postman seats got expensive, so I switched to Bruno. It stores API collections as plain-text .bru files you commit to Git — that’s the whole pitch.
Claude Opus 4.7 launched with the same price tag but a tokenizer change pushing real costs 1.0–1.35x higher. Plus Claude Design, Cursor Canvases, Copilot 4.7 GA, and Qwen3.6 beating Opus on a local benchmark.
Six stories that shook the developer timeline: BOJ’s 16-year run ends, Vercel’s OAuth-chain breach, Zig 0.16 promotes I/O to an interface, and more.
Cursor 3’s Plan Mode forces the AI to outline changes before writing code. Here’s how I use it for refactors, features, and bug fixes — plus when to skip it.
Four major AI updates dropped this week: Anthropic’s Claude Design preview, Cursor 3.1’s Agents Window polish, OpenAI’s GPT-Rosalind for life sciences, and Gemini 3 Deep Think upgrades.
Anthropic leased SpaceX’s Colossus 1 data center (220K GPUs, 300MW), doubling Claude paid limits. Plus two npm supply-chain attacks and GPT-5.5 Instant as default.