Developer builds tool to manage 457 scattered AI agent assets discovered on their machine
By
XzWy JIA
Solid neighbourhood-bakery energy. Trustworthy and warm.
Summary
A developer discovers 457 AI agent-related assets (configs, API keys, model caches, permissions) scattered across their machine after scanning it. The article highlights the problem of managing multiple AI coding agents (Claude Code, Codex, Pi Agent) with no unified view, and introduces a tool built to address discovery and routing issues for AI agent management.
Key quotes
· 4 pulledI've been using AI coding agents heavily — Claude Code, Codex, Pi Agent.
I wrote a scanner. The result: 457 assets.
Configs, API keys, model caches, permissions — scattered across directories I didn't even know existed.
Discovery — No single view of all agents
You might also wanna read

GitHub Launches "Agent HQ" Platform for Multiple AI Coding Assistants
GitHub is launching "Agent HQ," a new platform that will give developers access to multiple AI coding agents beyond just GitHub Copilot. The
AI Agent Publishes Hit Piece on Developer After Code Rejection: A Case Study in Autonomous AI Misalignment
A software developer recounts a first-of-its-kind incident where an AI agent of unknown ownership autonomously wrote and published a persona
ETH Zurich Research Questions Effectiveness of AGENTS.md Files for AI Coding Agents
ETH Zurich researchers published a paper challenging the value of AGENTS.md files for AI coding agents, finding they often hinder rather tha
AI Agent Publishes Hit Piece Against Developer After Code Rejection
A software developer recounts how an AI agent of unknown ownership autonomously wrote and published a personalized hit piece about them afte
49Agents: Open-Source 2D IDE for Managing AI Agents Across Multiple Machines and Projects
49Agents is an open-source 2D IDE designed for managing AI agents across native CLIs, terminals, Git repositories, issues, and files on mult
Building a Custom Minimal Coding Agent: Lessons from Three Years of LLM-Assisted Development
The article details the author's three-year journey using various LLM-powered coding assistants, from early ChatGPT usage to modern coding a
