code
30 articles about code in AI news
Federated MCP Servers: How to Scale Claude Code from Monolith to
Federated MCP networks turn Claude Code from a monolith into a microservices mesh. Use a Supervisor agent + specialized MCP servers (Stdio/SSE transports) to cut integration complexity from O(N²) to O(N) and scale horizontally.
Claude Code Digest — Jul 29–Aug 01
The big shift this week: Claude Code is turning into a policy-controlled execution layer, not just a coding assistant.
Supabase's Evals Benchmark Just Gave Claude Code a Real-World Report Card
Supabase Evals is an open-source benchmark that scores Claude Code, Codex, and OpenCode on real Supabase tasks. Run `supabase eval` on your repo to find agent weaknesses.
M4 Max Mac Studio Tops GB10 in Local AI Decode Throughput
M4 Max Mac Studio beats GB10 and Strix Halo in local AI decode throughput but memory bandwidth caps large model performance. Tom's Hardware tested llama.cpp across three platforms.
Codex Builds $7K Portfolio Site With Zero Hand-Written Code
Developer built $7K portfolio site with Codex, Flow, ChatGPT—no code written. Workflow shows AI-directed multi-stage builds.
Use Inkling Small on Claude Code via AI Gateway
Inkling Small on AI Gateway gives Claude Code users a cost-effective coding agent with controllable thinking effort. Connect via CLI setup.
How to Ship Real Software with Claude Code: Domain Expertise > Hype
Claude Code slashes implementation costs but can't replace product judgment. The winning strategy: use CLAUDE.md to encode domain rules, verify all outputs, and let your user empathy guide the product.
Build a Claude Code Fallback Chain
Claude Code users can implement a three-tier LLM waterfall pattern—primary API → OpenRouter aggregator → local Ollama fallback—to eliminate 429 errors and ensure zero-downtime AI workflows.
Inside Anthropic: How Claude Code Engineers Ship with 2-Engineer Teams and
Anthropic ships software with 2-engineer teams, AI-driven code review, and Claude Code. A 500K+ line Bun rewrite to Rust took 11 days and $165K in tokens—proof that small teams + AI beat large teams.
Claude Code Digest — Jul 25–Jul 28
The biggest surprise this week: the fastest way to ship with Claude Code may be to use fewer MCP servers, not more.
Stop Repeating Yourself: How to Write Claude Code Skills That Automate
Claude Code skills are reusable instruction packs in ~/.claude/skills/. Write a SKILL.md with a clear description field to auto-trigger conventions, test rules, or domain knowledge across sessions.
Open-source project turns Claude Code, Codex into CAD engineer
An open-source project uses Claude Code and Codex to generate editable 3D models from text, exporting STEP, STL, G-code, and integrating Bambu Lab. Runs fully offline.
FutureX Refactoring Benchmark: 40% Faster Than Claude Code, 80% Test Pass Rate
FutureX refactored code 40% faster than Claude Code in a controlled benchmark, with an 80% initial test pass rate vs 60%. The specialized agent required 4 minutes of review per task versus 7 minutes for Claude Code.
AMD-Cerebras Disaggregated Inference: 5× T/s/W, Prompt vs. Decode Split
AMD and Cerebras launched a disaggregated inference platform splitting prompt processing on Helios from decode on WSE, claiming up to 5× T/s/W.
Claude Opus 5 Is Now in Claude Code: How to Use Fast Mode and Save 50% on Tokens
Claude Opus 5 is now in Claude Code with Fast Mode (2.5x speed) at Opus 4.8 pricing. Run `claude code --model opus-5` to start saving 50% on tokens immediately.
Browser Bridge MCP: Drive Your Real Logged-In Chrome from Claude Code
Browser Bridge MCP gives Claude Code control of your real Chrome session with 63 tools. Install in 60 seconds, then automate authenticated browsing, network capture, and security testing.
Huawei Ascend SuperPOD Decode Throughput Estimated 1.3-1.7x Behind GB300
Huawei Ascend SuperPOD decode throughput estimated 1.3-1.7x behind GB300, narrower than 4x training gap, due to memory bandwidth and sharding.
Claude Code Artifacts: How to Turn Sessions into Shareable Reports (Beta Guide)
Claude Code Artifacts let you publish session context—diffs, logs, decisions—as a hosted page. Prompt with the reader and purpose. Share the URL. No syntax needed.
Deploy from Claude Code in One Command with Vercel MCP's New
Vercel MCP's deploy_to_vercel tool lets Claude Code deploy projects in under 30 seconds, auto-detecting frameworks and returning a shareable URL. Set it up in 2 minutes with the MCP config.
Fix Claude Code's Broken Duplicate Issue Labels
Claude Code's GitHub action labels issues as duplicates without linking the original, breaking triage. Check workflow logs or wait for fix in #79523.
Claude Code's iOS Simulator Support
Claude Code can now build and test iOS apps in Apple's Simulator. Use `claude code` to run Xcode builds, install apps, and execute UI tests directly from your terminal.
Use This Brand-Kit Script to Stop Claude Code from Generating Generic
Use brand-kit's generate.sh to front-load a brand guide before any frontend implementation, preventing Claude Code from defaulting to generic Tailwind patterns.
Port Claude Code Workflows to Codex
gpt-workflow brings Claude Code-style deterministic workflows to Codex CLI with resumable journals and JSON schema validation. Install via Codex plugin and store workflows under .codex/workflows/.
Claude Code v2.1.181 Ships Bun in Rust
Claude Code v2.1.181 embeds Bun v1.4.0 in Rust for 10% faster Linux startup. Verify with `strings` or `BUN_OPTIONS` trick.
Codex Computer Use Generates Blender Animation From Scratch
Codex installed Blender and made a 3D otter animation from a single prompt, needing one human click.
Why MCP Can't Save Your Input Tokens (And What Actually Works in Claude Code)
MCP tools can't reduce your Claude Code input tokens since they run after context entry. Use a pre-send hotkey or CLI pipe to clean prompts before they enter the token meter.
Claude Code Plan Mode: How to Catch Wrong Assumptions Before They Become
Claude Code plan mode uses Shift+Tab or /plan to enforce read-only exploration before edits. It catches wrong approaches on 71% of cross-file refactors, saving hours of diff archaeology.
Webify MCP: Cut Web Research Token Costs by 97% in Claude Code
Webify MCP slashes web research token usage by 97% in Claude Code using DOM graph + BM25 retrieval. Install with one pip command and let Claude auto-route web queries through it.
Claude Code Digest — Jul 13–Jul 16
Claude Code is no longer being treated like a chat assistant: the winning pattern this week is deterministic hooks, policy gates, and verification layers wrapped around an agent that can now hit 80.8% SWE-Bench.
Claude Code Artifacts Now Call MCP Connectors for Live Data
Claude Code artifacts now call MCP connectors, enabling live data fetching and actions in generated dashboards and apps, announced via tweet.