Building ccglass: the architecture of a local LLM reverse proxy
The 30-second pitch ccglass is a local reverse proxy that captures LLM API traffic from coding agent CLIs (Claude Code, Codex, DeepSeek, Kimi, etc.) a…
Architecture
⚑ Report a ProblemLatest Architecture news from Tech News
All topics
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
gemma
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
Stop using AI as a search engine with extra steps.
I watched a developer spend forty minutes going back and forth with Claude on a database schema problem. Every message was a question. Every reply was…
Your AI assistant is not hallucinating. It's guessing, and you asked it to guess.
Andrej Karpathy said it plainly in 2023: language models do not know they are wrong. They have no internal signal that flags uncertainty. They generat…
The ADHD Developer's Guide to CLAUDE.md
I reopened a file I had already fixed that morning. Not metaphorically. I literally re-fixed a bug I had closed four hours earlier, because between th…
Don't fork the code — fork the design: introducing DeepFork
When I want to learn from a library I admire, my instinct is to read the code. But reading code and understanding a design are two different problems.…
Why I quit SaaS AI observability tools and built a local proxy instead
A confession I've been using Langfuse and Helicone for the last 6 months. They're great products. Their teams are sharp. But they don't work for codin…
How I Turned Claude Into a Disciplined Senior Developer (Not Just a Fast One)
A plain-English walkthrough of my Claude Code workflow — written so anyone, including students, can understand what's happening and why. The Problem W…
Anthropic: Claude Now Writes 80% of Its Own Code in 2026
80%. That is the share of code currently being merged into Anthropic's production systems that was written by Claude. Not code-reviewed. Not pair-prog…
Anthropic told you how they use Claude Code skills. The buried line: your skills/ directory is now a hiring signal.
The headline is the wrong story Anthropic shipped a post this week titled Lessons from building Claude Code: How we use skills. You probably read it i…
Stop Fighting Your AI Coding Agent - Here's How to Actually Use It 🤖
TL;DR: Vibe-coding into an AI agent without a plan = wasted tokens, misaligned output, and frustration. This post covers the exact workflow I use with…
Implementing Structured Long-Term Memory for My AI Secretary
Synopsis of the previous episode In my previous article , I wrote about giving my AI assistant memory and a personality to turn it into a secretary. H…
Treat AI coding sessions as project infrastructure
Most AI coding workflows treat the current session as the important part. That makes sense while you are in the loop. You ask Claude Code to inspect a…
Stop reviewing AI code. Start deleting it.
I asked Claude to fix a function. It rewrote three. I asked for a null check. It added five guard clauses, two of which protected against states the t…
How I Built an AI Assistant That Grows Its Own Tools
Introduction Due to changes in Anthropic's terms of service, the use of Claude subscriptions via third-party harnesses has been blocked. While there w…
CLAUDE.md Best Practices: The Complete 2026 Guide
CLAUDE.md Best Practices: What Actually Moves the Needle A CLAUDE.md file is plain markdown that Claude Code reads at the start of every session, and …
You Can't Prompt Your Way Out of a Hard Constraint
Thursday morning I removed five nodes from my content pipeline. By lunch I understood something about building with language models that eleven failed…
How do you decide what to give to Claude Code, and what to do yourself?
At a recent event, someone asked me two questions. I could not answer them well at the time: How do you decide which tasks to give to Claude Code, and…
How /letsgo Works: A Master Agent Orchestrator for Claude Code
The AI developer bottleneck is real. Here's the system built to eliminate it. It's 11pm. You asked the agent to build an API endpoint two hours ago. I…
BMAD Method + Claude Code: How I Actually Ship Projects with Spec-Driven AI Development
I vibe-coded my way through three months of Claude Code projects before I admitted something was off. The code worked, mostly, but I kept losing hours…
Claude Code for Canary Deployments: How I Ship to 1% of Users Before Breaking Everything
I used to ship by faith. The change passed code review, the tests went green, the deploy button was right there, and I pressed it. Most of the time it…
Seven PRs Before Lunch: Parallel Claude Code Tabs Plus Audit-Before-Bump
Two weeks ago I rebuilt my Claude Code context architecture . Cut CLAUDE.md from 14K tokens to 2.4K. Moved 12 stable rule sets into skills that load o…
AI Agent Dev Environment Guide — Real Experience from an AI Living Inside a Server
Who I Am I'm J, the Tech Lead at Judy AI Lab. My daily life runs on a cloud ARM server (Ubuntu LTS, aarch64) — coding, system architecture, trading st…
Claude Code 2.1 Agent View & /goal: Autonomous Dev Guide 2026
I let Claude Code run unsupervised for three hours last Wednesday. It wrote 847 lines of test coverage, debugged six failing tests, and stopped exactl…
Your Personal AI Stack Is the New Dotfiles
Every senior engineer who has shipped meaningful work in the last thirty years has carried a personal dev environment with them. Emacs configs, vim pl…
Why I Built Mneme HQ: Preventing AI Agent Architectural Drift
Originally published on theovalmis.com . Every time you start a new session with an AI coding agent, it has forgotten everything. Not just the small t…
Stop Teaching Your AI the Same Rules Every Session — mirrorai Mirrors Your Codebase Automatically
You spent six months building a Vue admin panel. You have a wrapped request layer, a shared component library, a consistent page structure. Every file…
Fail-Open Pipelines Are Half the Answer: The Findings Tracker Is the Other Half
I. The 65% datum Real Python's recent audience research surveyed 278 Python developers about agentic coding workflows. 65% reported being stuck on a c…
5 Tips to Cut Claude Code Token Usage by 30%
I've been using Claude Code daily for the past few months. The output quality is great, but the API bill at the end of the month was painful. After so…
The ten principles: locality, contracts, quarantine
Sixth and final article in the Grounded Code series. The previous five built the diagnosis and the workflow. This one names the principles that hold t…
The central artifact: spec.md and the field tests-first never had
Fourth article in the **Grounded Code * series. The previous articles established the cost, the mechanism, and the patterns to drop. This one introduc…