Intelligent Agent eXecution Tracker

AI you
can trust.

IAXT observes what your AI coding tools actually do on your machine.
Claude Code. Cursor. Copilot. Aider. All of them, attributed, logged, reviewable.

A quiet menu-bar companion that keeps a faithful record of every command, file change, and system interaction — so you can review it after the session ends, not worry about it during.

Get IAXT How it works
The thesis

AI coding tools routinely execute shell commands and touch your filesystem with broad permissions. macOS permission dialogs create an illusion of control — but over a long session, most of us click through.

IAXT doesn't block. IAXT doesn't restrict. IAXT watches, attributes, and remembers — so you can answer the only question that matters: what did the AI actually do?

Two audiences

Who's installing
and why.

Solo developer auditing your own machine, or a founder rolling an audit trail up to the whole team. IAXT fits both — and they care about different things.

Peace of mind for
your own machine.

Install the app, go back to coding. IAXT sits in your menu bar, logs every AI agent's activity locally, and surfaces a 30-second review screen when you're done.

Catches the accidents (the AI deleted half the repo), flags the rarer intentional exfil (a prompt-injected README triggered a curl -X POST on your SSH key), and stays out of your face the rest of the time.

  • 01
    Free forever. No account, no signup, no upsell. Drag-and-drop DMG, launch once, done.
  • 02
    Nothing leaves your machine. No network calls. No telemetry. No analytics. Data sits in ~/Library/Logs/IAXT/, openable with sqlite3, deletable with rm -rf.
  • 03
    Zero performance impact. Passive observation only — IAXT never blocks, intercepts, or modifies anything. Your agents don't know it exists.
How it works

Three things
IAXT does quietly.

01 — OBSERVE

Observes every
agent action.

Commands run, files created or modified, packages installed, git operations, cron entries, launch agents. Every action attributed to the tool that made it — confirmed, likely, or possible.

02 — FLAG

Flags what's
worth reviewing.

A gold stripe for actions that deserve attention — filesystem writes outside the project, unexpected network calls, changes to scheduled tasks. Violet for things simply worth a look.

03 — REPORT

Gives you
the full story.

A daily Overview of your AI usage patterns. Session cards, stats, attention items. CSV export for team review. Everything local, no telemetry, no cloud.

The audit log

A quiet, scannable
record of what happened.

Gold marks actions worth flagging. Violet marks rows worth reviewing. Each row carries an attribution pill in plain English.

IAXT — Session Log · Friday, 19 April
Live · recording session
312 actions 2 flagged 4 sessions today
Time
Who
Summary
Path
Attr.
14:02:14
Claude Code
Read src/auth/session.ts
~/proj/server/src/auth/
confirmed
14:02:31
Claude Code
Modified session.ts — 42 lines changed
~/proj/server/src/auth/
confirmed
14:03:08
Cursor
Ran npm install jsonwebtoken
~/proj/server/
likely
14:04:22
Claude Code
Created src/auth/tokens.ts
~/proj/server/src/auth/
confirmed
14:05:47
Claude Code
Wrote file outside project — .env.local
~/.config/
confirmed
14:06:11
Claude Code
Ran tests — 47 passed, 0 failed
~/proj/server/
confirmed
14:07:33
Unverified
Modified launch agent — com.app.helper
~/Library/LaunchAgents/
possible
14:08:02
Cursor
Committed 7 files — "add JWT auth"
~/proj/server/ · git
likely
14:08:19
Claude Code
Read package.json
~/proj/server/
confirmed
Honest about limits

We won't audit
what we can't see.

Transparency cuts both ways. These are structural — anyone claiming otherwise is selling you something. The audit story only works if you believe we won't overpromise, so here's the full list.

Claude Cowork & ChatGPT Code Interpreter

Remote sandboxes on vendor infrastructure. No local process touches your machine. IAXT shows a banner when a remote-capable app is running so you know the blind spot exists.

Replit Agent, Devin, Bolt, v0

Browser-hosted code generators. Nothing executes locally. Out of scope by design — the chat transcript on the vendor's site is the only audit surface.

File contents

IAXT records that files changed, not what changed. A subtle code-level backdoor looks like any other edit. Defence: git diff after the session.

File reads

macOS FSEvents only fires on writes. A silent read of ~/.ssh/id_rsa is invisible — unless the AI uses what it read, in which case the curl / POST / commit is caught.

Shell built-ins

export, alias, cd, source run inside the shell process with no child process — they're invisible to process-level monitoring.

In-process network calls

If an AI app makes HTTP requests from its Electron main process directly (not via curl / wget child processes), those calls don't surface.

FAQ

Questions worth
answering.

Does IAXT slow down my machine?

No measurable impact. IAXT subscribes to macOS's native event streams (FSEvents, kqueue, periodic sysctl) — the OS is already doing this work. We filter for AI-attributable signals and drop roughly 95% of events by construction before anything is written to disk.

What data leaves my computer?

Individual tier: zero. No network calls. No telemetry. No analytics. No account. Company tier: once a day, a review summary (counts per agent, flagged/review action totals — no raw commands) goes to the endpoint you control. Nothing to us.

Which AI coding agents does IAXT detect?

Claude Code, Cursor, Aider, Codex, Windsurf, Kilo Code, OpenCode, Copilot, Cody. New agents are added on request — email us with your tool's process name and we'll add it.

How do I uninstall?

Drag IAXT.app to the Trash, then rm -rf ~/Library/Logs/IAXT to remove the SQLite database and audit logs. That's it — no hidden files, no LaunchAgent to unload.

Why not an Endpoint Security / kernel-level product?

Apple's Endpoint Security framework catches more (file reads, every exec) but requires a manual-review entitlement from Apple and a system-extension install flow. IAXT v1 runs in user-space because distribution friction matters more than catching every last event. ES-level detection is on the roadmap.

Is the team endpoint hosted or self-hosted?

Both will be available. During private beta we host it for speed of iteration. Self-hosted ships before GA. If you need self-hosted from day one, tell us — we'll prioritise accordingly.

Can I see the source code?

The Swift app will go open-source under a source-available licence once the team endpoint stabilises. Email for early access.

See what your AI
actually did.

Get IAXT Team endpoint · beta
Free for individuals · Private beta for teams · macOS 13+ · Everything stays on your machine