# agentwhy

> A local tool that reads saved Claude Code, Codex and Copilot conversations to show which private files an AI agent opened and which keys to change.

agentwhy is made by Karol Kozer. It reads the conversation records that Claude Code, Codex and GitHub Copilot already save on your computer and reports which private files (such as `.env` files and keys) an AI agent or its helpers opened, the task that led to it, and which key to change. It runs locally via `npx @agentwhy/cli`, and the repository lists a v0.4.2 release and an Apache 2.0 license.

## What It Is

agentwhy is a local security-visibility tool for people who build with AI coding agents. You run one command in your project folder, and a page opens on your computer listing conversations, the private files reached, who reached them, and what to fix. The project describes itself as pre-MVP. It processes records by fixed rules, with no AI model, account, or internet connection, and the README says secret values are replaced before a report is built.

## How the report works

The dashboard shows a week of conversations, each marked by whether a private file was opened. Opening a conversation shows a to-do list, a step-by-step story of what happened, a diagram, a by-folder view, and a full event record. It also traces helper agents: which helper was given what task, which files it touched, and what it passed back to the main agent. For each private file you can choose to block it, so the agent is stopped, or track it, so the agent may read it and you are told.

## Optional protection

`init` can add rules and hooks to Claude Code, Codex, and (when enabled) Copilot that refuse obvious reads of private files. It shows exactly what it will write and asks first, and `init --remove` undoes it. The documentation states this is not a sandbox: paths built at runtime, scripts, or commands handed to another shell can still get through, which is why the report reads what actually happened. The README also notes that the report can miss file access the transcript does not record, such as reads inside scripts or via connected MCP tools.

## Platform and agent support

It requires Node 22 or later and was made and tested on a Mac; Windows is described as still being tested. It supports Claude Code, Codex, and GitHub Copilot conversations, but not Cursor's AI, Windsurf, or chats on claude.ai.

## Features
- Reads saved Claude Code, Codex and Copilot conversations locally
- Shows which private files an agent opened and the task that led to it
- Traces helper agents and what they passed back
- Step-by-step, diagram, by-folder and full-record views
- Per-file Block or Track choices
- Optional hooks that refuse obvious secret reads
- Protection of paths outside projects via protect command
- Secret values stripped from reports
- Runs offline with no account and no AI model
- CLI commands: check, report, init, protect, notify

## Integrations
Claude Code, Codex, GitHub Copilot, VS Code

## Platforms
WINDOWS, MACOS, WEB, API, VSC_EXTENSION, CLI

## Pricing
Open Source

## Version
v0.4.2

## Links
- Website: https://www.agentwhy.dev
- Documentation: https://github.com/karolkozer/agentwhy#readme
- Repository: https://github.com/karolkozer/agentwhy
- EveryDev.ai: https://www.everydev.ai/tools/agentwhy