I built something in the same space but took a different approach — less fun, more engineering: Vox (https://github.com/rtk-ai/vox) — local TTS in pure Rust, no API key, no cloud dependency.

So I built RTK. It wraps commands and strips the junk before it reaches your context: rtk git status # instead of git status rtk find "*.rs" . # compact results rtk ls . # token-optimized tree rtk cargo test # just the test results

My rtk gain -q after 15 days of real usage: Total commands: 7,061 Input tokens: 29.3M Output tokens: 4.8M Tokens saved: 24.6M (83.7%)

Biggest surprise was rtk find — directory listings are insanely wasteful. Run rtk discover on your Claude Code session history to see how many tokens you've been wasting — that's what convinced me to actually build this. Rust, MIT licensed. Happy to hear what commands are the worst token offenders for you.

https://github.com/rtk-ai/rtk

Comments URL: https://news.ycombinator.com/item?id=46974740

Points: 4

# Comments: 4

An open-source multi-cloud governance framework powered by a YAML rule engine. We just reached a milestone by adding Database (DB) support.

The goal is to allow developers to audit configuration and compliance directly within DB instances, alongside standard cloud resources (AWS, GCP, Azure, K8s). We’re focusing on keeping the YAML rules as agnostic as possible so the same logic can apply across different environments without rewriting everything. rtk (https://github.com/rtk-ai/rtk)

This is a "scratching my own itch" project born from using Claude-code. While vibe coding, I got frustrated watching the agent spam ls -al or cat repeatedly just to "orient" itself.

It creates two main issues:

    The Token Tax: It burns through tokens for info the agent already has.

    Context Pollution: The context window fills up with redundant noise.

I developed and use an IA tool to save $$$ . https://github.com/pszymkowiak/rtk

Save your token on any IA code solution: rtk gain from a session:

  RTK Token Savings
  ════════════════════════════════════════
  Total commands:    650
  Input tokens:      3.9M
  Output tokens:     204.4K
  Tokens saved:      3.7M (96.2%)

  By Command:
  ────────────────────────────────────────
  Command                Count       Saved     Avg%
  rtk find                  38        2.1M    86.2%
  rtk git status            93        1.4M    85.4%
  rtk grep                  67       84.5K    50.3%
  rtk read                  63       49.9K    30.7%
  rtk ls                   121       14.5K    52.9%
  rtk git push             138        9.4K    91.3%
  rtk env                   28        8.4K    98.4%
  rtk run-test               9        6.4K    87.0%
  rtk summary               13        5.1K    70.3%
  rtk kubectl svc            9        3.0K    95.3%

Estimations:

  Tier             Quota Brut      Équivalent RTK
  Pro ($20)        6.0M tokens     ~24M tokens
  Max 5x ($100)    30.0M tokens    ~120M tokens
  Max 20x ($200)   120.0M tokens   ~480M tokens

Comments URL: https://news.ycombinator.com/item?id=46812499

Points: 1

# Comments: 1

Total commands: 41 Input tokens: 6.8K Output tokens: 1.8K Tokens saved: 6.0K (88.2%)

Command Count Saved Avg% rtk git status 11 2.8K 81.2% rtk grep 3 1.5K 31.9% rtk git push 22 1.3K 92.0% rtk ls 5 431 47.1%

Here is what I’m getting with it so far:

I’m putting it out there in case it's useful to anyone else. It's written in Rust.

P.S. This is just a tool I built for my own needs and decided to share. If you have constructive feedback on the Rust code or the logic, I'd love to hear it. If it's not for you, that's totally fine too—no need for "angry" comments, just trying to be helpful!

Comments URL: https://news.ycombinator.com/item?id=46734022

Points: 3

# Comments: 1