DEV Community: TryHackMyAI

I Built AgentSpend: A Rust CLI That Automatically Tracks AI Agent Usage and Finds Wasted Tokens

TryHackMyAI — Thu, 22 Oct 2026 13:53:05 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady

What I Built

AgentSpend is a local-first Rust CLI that scans local Codex session files for token usage and saves deduplicated totals to a local SQLite database.

Digging through agent log files to figure out your usage is annoying and tedious. I built this to make collecting that data automatic and private—everything stays on your machine.

Note: This is an early MVP. Cost calculations, waste detection and AI recommendations aren't built yet.

Demo

If you have Codex session records on your machine, you can run:

agentspend doctor agentspend scan agentspend status

(I haven't attached a video or terminal recording yet since I still need to verify the build and run live CLI tests.)

Code

Repository: https://github.com/aunjum/AgentSpend
Installation: Run cargo install --path . in the root directory.

How I Built It

Rust & Clap: For building a fast, lightweight native CLI.
Serde: To parse event metadata from session logs.
SQLite: To store usage totals locally without duplicates.

The log connector uses turn-level counters so it doesn't double-count cumulative thread totals. To keep things secure, prompt and response text are ignored entirely and local API credentials are never touched.

Note on Gemma: I plan to integrate Gemma down the road, but since it’s not working yet I'm not submitting this for the Gemma prize category.

Why Does Open Innovation Matter?

Local, open-source dev tools give you complete control over your data. You can inspect exactly how log collection works, adapt connectors to your own workflow and ensure your usage data never leaves your hardware.

My Agent Session

Omitted—I haven't collected structured metrics on the agent session used to build this yet.

The Lazy Payoff

No more grepping through log folders or manually tallying up session files. The scanner runs in seconds and handles the tracking for you.

Prize Categories

Primary: Overall Hacktoberfest Challenge
Gemma Category: Skipped for now (waiting until integration is functional).

Limitations and testing

Imports: Claude and Gemini log parsing aren't implemented yet.
Features: Cost tracking, real-time TUI and Ollama/Gemma log analysis are still on the roadmap.
Testing: Needs broader testing across different real-world session setups.

Six Months From Now AI Security Will Feel Obvious. Today, You Can Be Early.

TryHackMyAI — Wed, 21 Oct 2026 18:56:49 +0000

tryhackmyai.com

Everyone learns to build AI but almost nobody learns to break it

A world where chatbots, agents and AI tools run everything and no one knows how to defend them.

So instead of just worrying about it, let's built something together.

A community. A lab. A playground for the curious.

First learn. Then attack. Then defend.

That's TryHackMyAI.

You can start completely free.

Try the Launch offer today.

No giant commitment. No complicated choices.

Just one small step before deciding if this is worth going deeper into.

🔐 Break AI.
🧠 Understand why it broke.
🛡️ Learn to defend it.

Happy AI Hacking!

AI Can Be Hacked. I Built TryHackMyAI So You Can Learn How to Defend It.

TryHackMyAI — Wed, 21 Oct 2026 06:06:55 +0000

Break AI. Understand AI. Secure AI.
👉 Try free lessons and labs here: https://tryhackmyai.com

AI is everywhere. Most people learn to build it. Few learn to break it and secure it.

That’s the problem I’m trying to fix.

I built TryHackMyAI : a hands-on platform where you learn AI security by trying to break controlled AI apps then understanding how to defend them.

Instead of hours of theory you get practical labs.

You might try to:

Trick a chatbot
Leak hidden data
Misuse an AI tool
Find a weakness in an AI app

Then you learn why it worked and how to prevent it.

It’s for developers, students, security folks, AI builders, curious hackers and complete beginners.

You don’t need to be an AI expert.

Try it for free: https://tryhackmyai.com

I’m looking for early users to explore, break things and tell me what to improve.