groundy

developer tools

51 articles · rss

Top in developer tools

devtools

Alibaba's Open Code Review Moves AI Review Into the CLI, Not the PR

Alibaba's open-code-review moves AI code review from PR threads into the developer's terminal, front-loading feedback before push but isolating each author's review.

jun 04
devtools

Vercel Ships Experimental Native CLI Binaries to Cut the Node Startup Tax

Vercel's experimental native CLI binaries drop the Node.js runtime, targeting agent loops and CI pipelines that spawn vercel repeatedly and pay V8 startup cost on each call.

jun 04
devtools

Vercel Rebuilds Its Marketplace CLI for Agents Instead of Humans

Vercel's CLI now ships commands tuned for LLM callers, not human operators. The shift reveals how infrastructure tooling priorities invert when the primary caller is an agent.

devtools

Malicious npm Packages Hit Red Hat's Published JavaScript Clients

Malicious versions of 32 Red Hat npm packages carried a credential-stealing worm, published through the vendor's OIDC pipeline. Vendor namespaces are not a trust boundary.

devtools

OpenAI Upgrades Codex Right as Teams Weigh Leaving Claude Code

Codex 0.137.0 ships multi-agent persistence as OpenAI's free-months promo targets Claude Code teams, narrowing the switching window before Anthropic's June 15 billing change.

devtools

GitHub Copilot Moves to a Platform App, Decoupling From the Editor

GitHub's Copilot App anchors the AI assistant to the GitHub account rather than the editor, moving permission scope from per-developer to org-wide with agent merge authority.

devtools

How a VSCode Bug Let One Click Steal Your GitHub Token

A four-step exploit chain in github.dev steals full-scope GitHub OAuth tokens via a single link click, exposing every repo the victim can reach with no patch available.

devtools

GitHub Copilot and Productivity: What an Observational Dose-Response Study Measures

Observational Copilot-productivity studies measure who uses the tool, not what the tool causes. Selection bias makes every dose-response claim uninterpretable without.

more in this beat 1–43 of 43
  1. jun 01 devtools JetBrains Ships Codex Natively, Making Its IDE the Multi-Vendor AI Surface
  2. may 31 devtools Transformers.js v4 Moves Transformer Inference Into the Browser
  3. may 27 devtools Should Your Coding Team Upgrade to Opus 4.8? The Honest Tradeoff Math
  4. may 26 devtools Vercel Sandbox Gets CLI Access and Env Vars: A Push at the Agent Runtime Slot
  5. may 25 devtools Bun Rewrites Its Core From Zig to Rust, Putting Downstream Zig Bindings at Risk
  6. may 25 devtools Vercel Bets on Bun While Post-Acquisition Priority Drift Makes the Runtime a Vendor Decision
  7. may 25 devtools PromptArmor Shows Microsoft Copilot Cowork Can Be Tricked Into Exfiltrating Files
  8. may 25 devtools Anthropic Buys Stainless: OpenAI and Google Now Depend on a Rival for SDK Tooling
  9. may 24 devtools Rmux Brings a Playwright SDK to tmux Sessions for Agent Automation Workflows
  10. may 24 devtools Shai-Hulud Returns: 314 npm Packages Compromised in a Self-Propagating Supply-Chain Worm
  11. may 22 devtools Deno 2.8 Lands as Bun Gets Deprecated by yt-dlp: The JavaScript Runtime Field Is Reshuffling
  12. may 22 devtools Google Sunsets Gemini CLI on June 18: Forced Migration to Antigravity CLI Breaks Existing Automation
  13. may 22 devtools Malicious VSCode Extension Hit 3,800 Repos: What GitHub's Marketplace Trust Model Actually Verifies
  14. may 22 devtools Cursor's In-House Model Changes the Vendor Calculus for AI Coding Teams
  15. may 17 devtools Claude Code Adds Plugin Dependency Enforcement: disable Now Refuses to Break Transitive Chains
  16. may 17 devtools Claude Code v2.1.139 Adds Agent View: One Inbox for Background Sessions, Spacebar Peek, and /bg Promotion
  17. may 17 devtools Windsurf 2.2.17 Bundles Devin Review Into Every Self-Serve Plan
  18. may 17 devtools GitHub Copilot's New Multiplier Table: Opus 27x, Sonnet 9x, Codex 6x for Annual Subscribers on June 1
  19. may 17 devtools GitHub Copilot's Opus 4.7 Multiplier: 7.5x to 15x to 27x in 60 Days
  20. apr 28 devtools Pydantic AI v1.87 Closes the LangGraph Gap: Deferred Tool Calls, OpenTelemetry Eval, Stateful Compaction
  21. apr 28 devtools Claude Code vs Cursor vs Copilot After the April 2026 Reshuffle: How the Comparison Math Changed
  22. apr 28 devtools LangGraph 1.1.10's ToolNode Now Accepts list[Command | ToolMessage]: How That Splits From Pydantic AI
  23. apr 27 devtools GitHub Copilot Replaces Premium Request Units With Token-Metered AI Credits on June 1
  24. apr 23 devtools GitHub CLI v2.91.0 Turns On Default Telemetry: What gh Collects and How to Opt Out in CI and Agent Pipelines
  25. apr 23 devtools GitHub Copilot Drops Opus from Pro and Pauses Signups: The Forced Migration Facing Agentic Workflows (see also forced migration)
  26. apr 22 devtools LiteRT-LM v0.10.1 Ships Gemma 4 MTP Heads That llama.cpp Can't Access
  27. apr 22 devtools LACE Forces vLLM and SGLang to Rethink How Parallel Reasoning Threads Run
  28. apr 19 devtools ACP Registry Is Live: Zed and JetBrains Just Did for AI Agents What LSP Did for Language Servers
  29. mar 26 devtools JavaScript's Date Problem Is Finally Fixed: The Temporal API After 9 Years
  30. mar 23 devtools SWE-bench Verified Explained: What the Coding Agent Leaderboard Actually Measures (and What It Misses)
  31. mar 23 devtools Claude Code in GitHub Actions: A Complete Guide to Automated PR Fixes
  32. mar 14 devtools JetBrains' New Language Lets You Talk to LLMs in Specs, Not English
  33. mar 14 devtools Alibaba's Page-Agent: Control Any Website With Natural Language
  34. mar 13 devtools GitHub Copilot vs Cursor vs Claude Code: The 2026 AI Coding Showdown
  35. feb 26 devtools Rust Is Quietly Replacing Python in AI Infrastructure
  36. feb 20 devtools Claude Code Plugins: Anthropic's Official Plugin Ecosystem Explained
  37. feb 20 devtools Claude Code Plugins: Anthropic's Official Extension Ecosystem
  38. feb 18 devtools Prompt Engineering Patterns 2026: What Actually Works Now
  39. feb 17 devtools Rowboat: The Open-Source AI Coworker That Actually Remembers
  40. feb 14 devtools Natural Language to SQL: AI Is Finally Making Databases Accessible
  41. feb 14 devtools GitHub Models: Free LLM Access for Testing and Prototyping
  42. feb 13 devtools Tree-Sitter Code Indexing: The Secret to Better AI Code Understanding
  43. feb 13 devtools Claude Code /fast Mode: Is 6x Pricing Worth It?
about this beat editorial framing

Developer tooling stopped being a UX argument the moment AI agents started writing measurable fractions of production code. The interesting questions are now economic and architectural: how billing units translate across vendors when the same model runs at different multipliers, whether agent protocols converge or fragment across editors, and what happens to a team’s review discipline when a CLI assistant can land a fifty-file refactor before lunch. We cover that shift with comparative, numbers-first reporting rather than launch coverage.

The beat tracks four durable tensions. First, the pricing layer: flat-rate seats, token-metered credits, and premium-request multipliers each hide different costs, and the right tool depends on which workload you’re forecasting. Second, the interop layer: agent-to-editor protocols, model-context standards, and SDK-generation pipelines are quietly consolidating under a few vendors, creating dependency risk for everyone downstream. Third, the runtime and language-tooling churn that AI workflows amplify, from JavaScript runtime reshuffles to memory-safety rewrites that break bindings teams didn’t know they had. Fourth, the governance surface that grows every time a CLI ships default telemetry, a plugin manager enforces transitive dependencies, or an in-IDE assistant gains autonomous execution.

What you won’t find here is a feature-by-feature roundup of whichever assistant shipped this week. We benchmark on real codebases, price the math out across plans, and flag when a “small” tooling change quietly rewrites a team’s review process, security posture, or vendor exposure.