Web Browsing Tools for CLI Agents: Three Tiers on the Capability Axis
From WebFetch to Computer Use — the landscape of web tools available to CLI agents, the tradeoffs across speed, safety, and site coverage, and recommended combinations for common use cases.
Read More
Deep Dive into Claude Code Harness - Chapter 1: Memory Management
What makes the Claude Code harness best-in-class? Let's dive into its leaked source code to learn about the rigorous engineering within. Turns out, its memory management is remarkably similar to the wiki system described in my previous post.
Read More
Introducting Wiki-Skills: Agent Skill for Managing Markdown Vaults
Kaparthy shared a viral note about a building an LLM-managed 'personal wiki' - which I interpret as a specific instance of a locally stored markdown vault. Here, I present Wiki Skills - a set of agentic Skills that captures the process of creating, querying, and updating this knowledge vault.
Read More
Autoresearch: Autonomous Hill-Climbing for Any Optimizable System
Run optimization experiments while you sleep
Read More
Good Dependency Hygiene Practices: Protecting Yourself from Supply Chain Attacks
The number of high-profile supply chain attacks on PyPI and npm has been increasing in frequency. Keeping good 'dependency hygiene' can help you stay protected. This post explores a list of simple actions you can take to achieve good hygiene, and an explainer on what they protect against.
Read More
Enabling Claude Code's voice mode in WSL
Claude Code now ships with a native `/voice` command, which performs speech-to-text (poorly) within the Claude Code CLI. Nevertheless, this feature is not available in WSL by default because Claude Code isn't able to detect audio input. This post is a fix.
Read More