MonClaw: A Minimal OpenClaw Built with the OpenCode SDK
Openclaw captures something magical: a useful AI assistant. If you squint, a useful assistant and a coding agent are quite alike. This post discusses building a minimal implementation using the Opencode SDK.
Taking a Look at OpenClaw (Clawdbot)
Openclaw/Moltbot/Clawdbot is taking the world by storm. What is it? How does it work? Let's take a look.
Exploring UCP: Google's Universal Commerce Protocol
Google just released the Universal Commerce Protocol (UCP), and I looked into it to understand what it is and how it works. This post shares my findings, including an overview of the standard, the underlying architecture, and practical, hands-on examples.
Building A Coding Agent (Provider-agnostic)
A Provider-Agnostic Coding Agent built using Python and Litellm
Notes on Distributed Consensus and Raft
How and why distributed systems like Kafka and Kubernetes remain in-sync across multiple machines thanks to the Raft algorithm.
Exploring Kafka Cruise Control
A hands-on introduction to Kafka Cruise Control, showing how to set it up, observe a real imbalance, trigger a rebalance, and explore the core ideas behind how Cruise Control collects metrics and makes optimization decisions.
Is MCP Worth the Hype?
Saying that Model Context Protocol (MCP) adoption has been explosive is almost an understatement. This post examines MCP and the problem it solves, while also digging into the issues it faces.
Exploring Prometheus Internals: TSDB and XOR Encoding
How Prometheus Monitoring work? This deep dive explores monitoring, alerting, TSDB and Gorilla XOR encoding!
It's Not Always DNS: Exploring How Name Resolution Works
An exploration of DNS and Name-to-IP translation. This deep dive explores NSS, getaddrinfo, systemd-resolved and more!
The Internet is Cool. Thank you, TCP
What is TCP? This post is an exploration of TCP, the workhorse of the internet. This deep dive includes detailed examples and a step-by-step walkthrough. A simple TCP explanation.
Inside Multi-Platform Docker Builds with QEMU
A deep dive into how Docker uses QEMU and binfmt-misc to build and run multi-architecture container images, enabling cross-platform support for x86, ARM, and beyond.
A Practical Tour From Source to CPU
A guided tour through how code becomes something a computer can actually run. The post explores how languages like C, Python, Java, and Go build, package, and execute programs. How they link libraries, manage dependencies, and interact with native code.
Reducing Context Bloat with Dynamic Context Loading (DCL) for LLMs & MCP
DynamicContextLoading is a lightweight technique for on-demand tool activation in LLMs and MCP, reducing context bloating by loading tools only when needed.
Exploring the Agentic Commerce Protocol (ACP)
Explore how the Agentic Commerce Protocol (ACP) lets AI agents shop on your behalf, from product discovery to secure checkout, using shared payment tokens and merchant integrations. This post breaks down the workflow, key components of AI-driven e-commerce.
Exploring Terminals, TTYs, and PTYs
This post takes a look at terminals, TTYs, and PTYs. We'll look at terminal emulators display text and styles. Along the way, you'll see escape codes, line discipline, signals, and a simple Python example with Pyte to show what's happening behind the scenes.
How Coding Agents Actually Work: Inside OpenCode
A hands-on exploration of OpenCode, an open-source coding agent built with a client/server architecture. Learn how AI tools, LLMs, and real-world constraints come together to create a powerful developer experience.
Is MCP a Security Nightmare?: A look into MCP Authorization with OAuth2
Exploring MCP's security and how it uses modern OAuth2 workflows and adjacent RFCs to enhance security and authorization.
Exploring Kafka Streams Internals
A Look Under the Hood of Kafka Streams
Taking a Look at Database Disk, Memory, and Concurrency Management
Buffer Pools, transactions, concurrency management and all that good stuff.
Meta MCP: Chaining Tools via Prompt-Driven Arguments
This post explores the concept of an MCP tool that can chain multiple tools within a single request, where the arguments for each tool can be dynamically generated using prompts based on the outputs of previous tools.
Behind Sending Millions of Messages Per Second: A Look Under the Hood of Kafka Producer
Exploring the code behind the Kafka Producer client.
Gossip and Consensus: Using Serf and Raft to Build a Kafka-esque System
We play with Serf and Raft to implement cluster mode for Monkafka.
How Are Images REALLY Stored?
Learning about image formats.
Taking a Look at Compression Algorithms
Dissecting various compression algorithms.
MonKafka: Building a Kafka Broker from Scratch
An attempt to implement a basic Kafka broker.
Exploring Apache Kafka Internals and Codebase
Trying to dig into the Apache Kafka codebase and make some sense of it.