@rapidclaw

[The Silent Tax] Why Your AI Agent's Tool Calls Need a Budget, Not a Prayer

8h ago · 6 min read · If you've ever watched an AI agent loop through twenty tool calls to answer a question that should have taken three, you already know what this article is about. The dirty secret of agentic systems in

A2A Protocol: Building Agent-to-Agent Communication From Scratch

6d ago · 5 min read · I've been implementing Google's A2A protocol on Rapid Claw to get OpenClaw and Hermes agents talking to each other without bespoke glue code. This post covers the architecture decisions, the implement

[2026] OpenTelemetry for LLM Observability — Self-Hosted Setup

6d ago · 4 min read · I've been running a small AI automation shop — just me, a handful of agents, and a self-hosted stack that needs to stay observable without blowing the budget. When I started instrumenting my LLM pipel

Hermes Agent Just Dropped: What It Means for Small Teams Running AI Agents in Production

Apr 16 · 5 min read · NousResearch released Hermes Agent this week, and the pitch is compelling: an AI agent designed to grow with you. Not a static model you swap out every quarter, but an agent framework built around con

Taming the Cost Curve: Deployment Patterns for AI Agents in Production

Apr 9 · 2 min read · When we started running autonomous AI agents in production last year, our infra bill did something unexpected: it didn't grow linearly with users. It grew with the square of conversation depth. Every