tooling
30 articles about tooling in AI news
Ethan Mollick: Current AI Tooling Is a 'Substitute' for Continual Learning
Ethan Mollick observes that the entire ecosystem of prompts, skill files, and retrieval tools is a patch for AI's inability to learn continually. If solved, this would rapidly obsolete much current tooling.
OpenAI Acquires Developer Tooling Startup Astral, Maker of Ruff and uv
OpenAI has acquired developer tooling startup Astral, known for creating the high-speed Python linter Ruff and package manager uv. The acquisition is positioned as a boost for OpenAI's Codex team, with plans to continue supporting Astral's open-source projects.
Anthropic Acquires Stainless for ~$300M, Owns MCP Toolchain
Anthropic acquired Stainless for ~$300M, gaining the dominant MCP server generator and key SDK tooling, signaling a bet on integration-layer moats over model differentiation.
Developer Ranks NPU Model Compilation Ease: Apple 1st, AMD Last
Developer @mweinbach ranked the ease of using AI coding agents to compile ML models for NPUs. Apple's ecosystem was rated easiest, while AMD's tooling was ranked most difficult.
Google's 'Agent Smith' AI Tool Reportedly in Internal Development, Joining OpenAI 'Spud' and Claude 'Mythos'
A leak suggests Google is developing an internal AI tool codenamed 'Agent Smith,' reportedly popular with employees. It's positioned alongside upcoming releases from OpenAI and Anthropic, signaling a new phase of internal productivity tooling.
Andrej Karpathy: AI Agent Failures Are 'Skill Issues,' Not Model Capability Problems
Andrej Karpathy argues most AI agent failures stem from poor user instructions and tooling, not model limitations. He advocates delegating 20-minute 'macro actions' to parallel agents and reviewing their work.
Anthropic's Accidental Code Release: Inside the Claude Code CLI That Wasn't Meant to Be Seen
Anthropic's Claude Agent SDK inadvertently includes the entire minified Claude Code CLI executable, revealing the inner workings of their AI coding assistant. The 13,800-line bundled JavaScript file contains everything from agent orchestration to UI rendering, raising questions about security and transparency in AI tooling.
Google's gws CLI: The AI-Agent-Ready Tool That Dynamically Masters Workspace APIs
Google has open-sourced gws, a CLI tool that dynamically interfaces with all Google Workspace APIs and ships with built-in AI agent skills. It eliminates custom tooling and automatically adapts to new API endpoints.
Nvidia Unveils Physical AI Agent Skills, 32B VLA Model at CVPR
Nvidia launched physical AI agent skills and a 32B VLA model at CVPR to automate AV and robotics workflows, addressing the fragmented tooling bottleneck.
The Universal MCP Server Pattern: How to Connect Claude Code to Any API in Minutes
Learn the universal MCP server pattern that connects Claude Code to dozens of APIs using minimal tooling, based on a real developer's build.
Reticle: A Local, Open-Source Tool for Developing and Debugging AI Agents
A developer has released Reticle, a desktop application for building, testing, and debugging AI agents locally. It addresses the fragmented tooling landscape by combining scenario testing, agent tracing, tool mocking, and evaluation suites in one secure, offline environment.
GitHub Repository Unleashes 1,715+ Production-Ready AI Agent Skills
A new GitHub repository has surfaced containing over 1,715 production-ready AI agent skills that developers can install and deploy in seconds. This collection represents a significant leap in accessible AI tooling, potentially accelerating agent-based application development across industries.
MCP Lead Enrichment Server Meters Billing at 0.6 Confidence
A Cloudflare Workers-hosted MCP server gives AI agents metered B2B lead enrichment, billing only when confidenceScore exceeds 0.6. The Zod-validated tools target hallucination and cost control in autonomous SDR swarms.
Claude Code Now Supports AGENTS.md: The Cross-Agent Standard Is Here
Claude Code supports AGENTS.md (issue #6235). Use AGENTS.md for team-shared rules, CLAUDE.md for Claude-only tweaks. This keeps configs portable across Codex, Amp, and Cursor.
Spatial Memory Agent: Frozen VLMs Learn From Experience
Spatial Memory Agent improves spatial reasoning in frozen VLMs via experience distillation and calibrated retrieval, without parameter updates. No benchmarks disclosed, so efficacy unverified.
Qwen 3.7 27B Draws Best Local-Model Pelican, Simon Willison Says
Qwen 3.7 27B, as a 17GB GGUF, drew Simon Willison's best local pelican-bicycle image. Signals on-device generation crossed a quality threshold.
Stanford, Northeastern Build 'Git for AI Agents'
Stanford and Northeastern built 'Git for AI agents,' version control for agentic workflows. The tool solves record-keeping gaps, but details are thin.
SemiAnalysis: Linux Runs Claude Shell Commands 3x Faster Than Windows
SemiAnalysis analyzed 2.91M Claude tool calls, finding Linux executes shell commands 3x faster than Windows, reshaping agentic AI latency priorities.
C# SDK for MCP 2.0 Ships with Streaming, Native AOT Support
Microsoft's C# SDK for MCP 2.0 adds streaming, native AOT, and DI improvements for .NET AI agents, signaling enterprise adoption of the Anthropic-originated standard.
Octopus Deploy's MCP Server: The Missing Onboarding Tool for Kubernetes Teams
Install Octopus Deploy's MCP server via `claude mcp add` to let Claude Code query environments, inspect releases, and trigger Kubernetes deployments—cutting onboarding friction and context-switching for ops teams.
How to Test and Debug MCP Servers for Claude Code: A Production Guide
Unit-test tool logic, mock external services, and add integration tests for MCP servers. Claude Code's MCP integration demands observability beyond local demos.
Meta Ships Muse Code Beta, Its First Coding Agent
Meta released Muse Code beta, its first coding agent built on Muse Spark 1.2. The release enters a market led by GitHub Copilot and Amazon CodeWhisperer.
Agent Plugins 1.0.0: The Portable Plugin Standard That Makes MCP Servers
Agent Plugins 1.0.0 standardizes MCP server packaging into portable plugins. Claude Code users can create a plugin.json manifest to share tools across ChatGPT, Cursor, Copilot, and more.
Stanford Public Course Puts Self-Improving AI Agents in Open
Stanford publicly released CS 329S Lecture 1 on self-improving AI agents, taught by Chowdhery and Mirhoseini. The course centers verifier-based sampling and names verification as the key unsolved challenge.
Claude Code Digest — Aug 01–Aug 04
Claude Code is no longer just a coding assistant — it’s becoming a policy-controlled execution layer, and the biggest wins now come from making agents stateless, auditable, and selectively specialized.
Model Routing Cut This Dev's Claude API Spend 35%
A developer cut Claude API spend 35% by routing tasks across Opus, Sonnet, and Haiku. Quality on hard tasks rose because Opus stopped handling busywork.
InAgent Hits 90.2% on OSWorld, First Agent Past 90%
InAgent scored 90.2% on OSWorld, first above 90%, with 100% on system-level tasks, surpassing OpenAI, Google, and Anthropic records. Harness engineering, not raw model power, drove the result.
DeepSeek-V4-Flash Open-Sourced: 304B Model Beats V4-Pro at $0.14
DeepSeek open-sourced V4-Flash-0731, a 304B model scoring 82.7 on VulcanBench, matching Claude Opus-4.8 at $0.14/M input tokens.
Beyond CLAUDE.md: The 2 Files This Developer Says Cut Repeat Errors in
Adopt TODO.md and AUDIT_LOG.md with CLAUDE.md. The audit log slashes repeat errors; the todo keeps Claude Code aligned with your roadmap.
ChatGPT Work Adds Browser, Cloudflare Deploys
ChatGPT Work adds a browser with screenshots and deploys web apps to Cloudflare Workers, per Simon Willison. The deployment capability, branded 'ChatGPT Sites', positions OpenAI against Vercel and Replit.