📰 Dev.to · WonderLab

Workflow Series (10): Enterprise Architecture — Registry, Composition, and Governance

Workflow Series (06): Security — Cross-Step Injection Propagation and Four Defense Principles

Open Source Project #107: page-agent — A Pure-JS GUI Agent for the Browser, No Screenshots, No Plugins, No Backend

Skill Series (05): Skill Workflow Chaining — 4 Patterns, Real Data, Parallel Speedup 1.5x

Skill Series (01): Skill Evaluation — How to Quantify AI Skill Quality

Open Source Project #101: Penpot — The Open-Source Design Tool That Speaks CSS Natively

Open Source Project #100: OpenMemory — A Real Cognitive Memory Engine for AI Agents

Agent Series (22): Context Engineering Deep Dive — Quantifying Three Context Management Strategies

Agent Series (20): Harness in Production — From Single File to Reusable Package

Agent Series (19): Harness Engineering — Complete 8-Layer Framework

Agent Series (17): Harness Engineering — Putting a Safety Harness on an Autonomous Agent

Agent Series (14): Agent Observability — Tracing Every Decision, Making the Black Box Transparent

Open Source Project of the Day (#87): BaiLongma - Equipping LLMs with 'Proactive Consciousness' and Initiating the ACI Era for Agents

Agent Series (9): Multi-Agent Architecture Design Patterns — Supervisor vs Pipeline

Open Source Project of the Day (#82): SkillOpt - Training LLM Agent Skills Like Neural Networks

One Open Source Project per Day #79: Twenty - Defining the Modern Open-Source CRM Alternative to Salesforce

Agent Series (6): Memory Management — Teaching Your Agent to Remember What Matters

One Open Source Project a Day (No. 77): notebooklm-py - Turning Google NotebookLM Into a Programmable API, With Claude Code Integration

Agent Series (5): Intent Recognition and Routing — Making Agents Actually Understand Users

Agent Series (4): Deep Dive into Tool Calling — The Agent's Hands and Eyes

Agent Series (3): Plan-and-Solve — Think First, Then Act

One Open Source Project a Day (No. 72): Andrej Karpathy Skills — Fix Four Chronic LLM Coding Problems With a Single CLAUDE.md

Agent Series (1): What Is an Agent — It's Not Just an LLM That Can Call Tools

RAG Series (15): CRAG — Self-Correcting When Retrieval Falls Short