Jamie's Blog

The curious developer's ODYSSEY, Exploring the Universe of TECH, CODE & AI.

The Self-Improvement Agent in Hermes: A Deep Dive

Staff-engineer-level notes on Hermes Agent's procedural self-improvement loop: how the runtime turns solved problems, user corrections, and hard-won debugging paths into durable skills without interrupting the foreground task.

Posted by Jamie Zhang on Friday, May 29, 2026

Exception Handling for LLM Calls in Production Agentic Systems

A deep dive into agent/auxiliary_client.py from Hermes Agent. Written for engineers building production agentic applications who need to go beyond 'catch Exception and retry.'

Posted by Jamie Zhang on Wednesday, May 27, 2026

Designing Context Compression for Production Agents: A Deep Dive into Hermes

Staff-engineer-level notes on agent/context_compressor.py: how Hermes preserves task continuity when a long-running agent outgrows the model context window, and what the implementation teaches about summarization, compression, and failure-tolerant agent design.

Posted by Jamie Zhang on Sunday, May 24, 2026

Hermes Agent — Deep Dive Learning Notes

Staff-engineer-level notes for senior AI engineers designing and implementing production agents. Written after reading run_agent.py, model_tools.py, toolsets.py, agent/, and tools/ in full.

Posted by Jamie Zhang on Thursday, May 21, 2026

Building a Multi-Platform Agentic Gateway: A Deep Dive into Hermes Gateway

A Staff-Engineer-level study of the Hermes Agent messaging gateway — from process lifecycle to platform adapters, session management to streaming delivery, and the design patterns that make it production-grade across 15+ messaging platforms.

Posted by Jamie Zhang on Tuesday, May 19, 2026

Building Production Agentic CLIs: A Deep Dive into Hermes

A Staff-Engineer-level study of the Hermes Agent command-line interface — from filesystem layout to REPL internals, model selection to plugin extensibility, and the design patterns that make it production-grade.

Posted by Jamie Zhang on Sunday, May 17, 2026

Inside Claude Code: The Architecture of a Production-Grade System Prompt

A deep dive into Claude Code's prompt architecture — how it uses modular design, strict caching boundaries, and negative constraints to build a production-grade agentic system.

Posted by Jamie Zhang on Thursday, May 7, 2026

What Claude Code's Source Code Taught Me About Building Production AI Agents

A Staff Engineer's deep-dive into Claude Code's source code — the architectural patterns, trust boundaries, and self-healing mechanisms that make a production CLI agent work.

Posted by Jamie Zhang on Monday, May 4, 2026

Self-Hosting Agentic AI: A Deep Dive into the OpenClaw Architecture

An in-depth technical exploration of OpenClaw, an open-source agent runtime. We examine its hub-and-spoke architecture, gateway control plane, and the networking challenges of deploying agentic systems within enterprise VM environments.

Posted by Jamie Zhang on Friday, April 24, 2026

How LLMs Work: An End-to-End Guide from Pre-training to Prediction

A deep dive into the complete lifecycle of a Large Language Model, from pre-training and fine-tuning to the inner workings of the decoder-only transformer architecture during inference.

Posted by Jamie Zhang on Wednesday, February 25, 2026