Your MCP Hub Exposes Every Tool to Every Agent. That's the Bug.
We stood up an internal MCP hub last quarter. It aggregated four services behind one endpoint, listed every tool in a single catalog, and let any co…
Architecture
⚑ Сообщить о проблемеПоследние новости Architecture от Tech News
Все темы
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
news
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
Drift Checks in TDK CLI: Fail Fast, Generator Changes, and Catching Hand Edits Before Commit
A drift check answers one question: has someone changed a generated file by hand? TDK runs that check before Tilt starts, so a hand edit stops the s…
Python GA on Vercel, New Reasoning Models, and Layout-Aware Diffusion: Issue #110
This week's releases cluster around a clear theme: reducing the infrastructure surface area developers have to manage. Vercel made a serious push to…
11 MCP Servers That Prove MCP Isn't Dead
Disclosure: I'm the founder of PDFHaul, which is #5 on this list. Originally published on the PDFHaul blog , where the full source list with links l…
Six dev.to Articles Walked In, Four Roadmap Phases Walked Out: Why the Community Is the Best Design Review Your Project Will Ever Get
One evening of reading other people's posts about agentic coding turned into three new global rules on my machine, four new phases on cairn's roadma…
The basics, done carefully
Small things decide whether a tool feels solid: what a bare command does, what happens in a pipe, and how the CI log reads. Here is how vx handles e…
Haiku 5.5 Slashes Costs; New Agents Reshape Docs
This week's tooling news splits neatly into two themes: pricing traps disguised as savings, and a quiet consolidation of agentic infrastructure unde…
Email Test Fixtures Need a Trust Boundary Map
Email verification tests are often treated as a small automation detail: create an address, wait for a message, click a link, and delete the fixture…
LoreConvo: every session starts warm
Most AI sessions begin with a blank slate. You open Claude Code, pick up where you left off in a data pipeline, and spend the first few minutes re-e…
Claude 5.5 + Vercel Gateway: 30% faster, cheaper, and a cleaner security model for agents
This week landed a rare combination: a meaningful model upgrade that's a genuine drop-in replacement, plus infrastructure changes that reduce operat…
25 of 26 rules in a 755-line AGENTS.md changed nothing
I keep seeing teams treat their AGENTS.md like a config file: write the rules once, assume the agent obeys. So I went looking for anyone who actuall…
Why AI Coding Agents Need Project Memory, Not Just Bigger Context Windows
Why AI Coding Agents Need Project Memory, Not Just Bigger Context Windows AI coding tools are becoming part of everyday development. They can explai…
Our CLAUDE.md and skills named 190 commands: one pointed at a deleted script for 24 days while 28 shape tests passed
Our CLAUDE.md, three rules files, nine skills and one CLI reference contain 707 pnpm <name> references to 190 unique names, checked against 19…
Claude Opus 5.5: 40% cheaper, frontier-grade performance
This week was dominated by cost compression and gateway consolidation. Claude Opus 5.5 dropped with a meaningful price cut and no code changes requi…
The missing layer in AI tooling: sharing what your assistant already knows
It took my AI months to learn how I think, code, and ship. When a teammate joined the project, their AI started from zero — same codebase, same conv…
Choosing between managed gateways and self-hosted libraries for LLM routing in 2026
Choosing between managed gateways and self-hosted libraries for LLM routing in 2026 The best router depends on who controls the infrastructure, not…
A self-hostable AI workstation with a coding agent and answer-checking (Flywheel 1.0.1)
Flywheel is a self-hostable AI workstation and coding harness. You run it on your own machine, point it at any model you hold a key for or a local o…
Developer Tools Beyond IDEs: 10 Systems for Modern Architectures
Developer Tools Beyond IDEs: 10 Systems for Modern Architectures Integrated Development Environments (IDEs) are architecturally constrained to singl…
Routing OpenCode Tasks with Jev
After the release of the TypeSafe AI Jev model and its availability in OpenRouter, I decided to immediately test its capabilities and rewrite my min…
Your coding agent remembers more than MEMORY.md — so I built a local inspector for it
I've been using AI coding agents heavily, and I kept running into the same problem: Useful context doesn't live in one place A coding agent may have…
How to Stop Cursor and Copilot from Turning Your Codebase into Spaghetti
AI coding assistants like Cursor, GitHub Copilot, Claude Code, and Windsurf have completely revolutionized developer velocity. Being able to scaffol…
The 300-line instruction budget: what actually fits in your agent config
Ask five developers what belongs in a CLAUDE.md and you will get five files between 40 and 900 lines. The useful question is not "what can I put in"…
Before You Integrate DeepSeek Harness, Test These Three Things
A trending repository can be worth testing without being ready for your roadmap. Stars show attention. They do not show whether an integration will…
Ephemeral Generators Need a Review Boundary
A free model and a free server change your budget, not your threat model. The interesting engineering problem is the boundary around the generator.…
Is Your Site Even Visible to ChatGPT?
You've optimized for Google. Sitemap's clean, Core Web Vitals are green, structured data validates. But when someone asks ChatGPT or Perplexity abou…
I Built Markups: A Free, Open-Source Markdown Editor That Doesn't Need an Account
Markdown is one of those formats developers end up using almost everywhere. README files. Documentation. Architecture notes. API docs. Project speci…
Learn how Antigravity Usage Intelligence lets you monitor token consumption, cache savings, and quotas in Google’s Antigravity IDE.
Figure: Example Antigravity Usage Intelligence dashboard in VS Code, showing token usage charts and quotas. For developers building with Google Anti…
Daxon: Bringing a Complete Data Intelligence Workspace Into VS Code
What if your data tools lived where you already write your code? We built Daxon to answer exactly that. Daxon is an all-in-one Data Intelligence &am…
Stop Shipping Architecture Diagrams That Cannot Be Verified
It is 3:00 AM, database connections are dropping, and the on-call engineer is staring at a diagram routing traffic through a cluster decommissioned…
OpenHands Just Hit 1.0. Here's How to Run It on Your Own Machine Without Handing Over the Keys
This morning two pieces of agent news landed within hours of each other. GitHub announced that Copilot Workspace now runs multiple specialized agent…