@juancolamendy

MemoryBank in Google ADK and Agno: Building Agents That Actually Remember

3d ago · 21 min read · Your AI agent just burned $47 in tokens re-processing context it saw yesterday. Meanwhile, your user is typing the same preferences for the third time this week, wondering why your "intelligent" assis

How I Built My Own OpenClaw Bot V3: Teaching My AI to Delegate

Mar 31 · 18 min read · I got V2 working. The brain was modular, the skills system was clean, and the agent knew what it could do without being told every session. Then I tried to make it do two things at once. Research a to

How I Built My Own OpenClaw Bot V2: Skills, Context Files, and a Smarter Brain

Mar 23 · 14 min read · I built a persistent AI assistant. It remembered me, ran commands, and actually worked. Then I used it daily — and watched it fall apart. It couldn't discover its own capabilities. It forgot what I di

How I Built My Own OpenClaw Bot

Mar 16 · 18 min read · I fell in love with OpenClaw. Started investigating how this amazing bot works. Really to understand how it works under the hood and improve my skills to build AI agents. This is the story of how I we

Mastering Workflow Orchestration: A Deep Dive into Steps, State Management, and Conditional Logic in Agno

Feb 9 · 17 min read · Your AI agent works flawlessly—until you need it to collaborate with three others. Here's the brutal reality: 73% of developers abandon their multi-agent projects within the first sprint, drowning in spaghetti code, race conditions, and state managem...