rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Runssource: GitHubhomepageRustApache-2.0commit 475f9ddfc20d
Rust, Apache-2.0 licensed. The project labels itself: agentic coding, ai coding, anthropic, claude code, cli, command line tool, cost reduction and developer tools.
rtk runs. An Argusic agent installed it in 6 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
RTK (Rust Token Killer) v0.42.4 builds from source, passes all 2936 tests with 0 failures, and runs as a working CLI proxy producing token-compressed filtered output for ls, git, cargo, and other commands.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 80 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
- Install time
- 6 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- cargo test: 2853 unit + 83 integration passed, 0 failed; binary rtk --version prints 0.42.4; rtk ls lists files; rtk gain shows 82.7% savings dashboard; rtk cargo build re-runs
- Model tokens used
- 54,377
- Exact commit tested
- 475f9ddfc20d
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Everything built and tested cleanly with zero errors. Here's the final summary: **Install**: `cargo build` succeeded on first try — no dependencies missing, no compilation errors. **Tests**: `cargo test` — 2853 unit tests + 83 integration tests across 7 test files all passed. 0 … **Binary verified**: `rtk --version` prints `rtk 0.42.4`. `rtk ls` produces compact filtered direct… **Release build**: `cargo build --release` succeeded, release binary also runs and reports same ver… tokens used 54,377 Everything built and tested cleanly with zero errors. Here's the final summary: **Install**: `cargo build` succeeded on first try — no dependencies missing, no compilation errors. **Tests**: `cargo test` — 2853 unit tests + 83 integration tests across 7 test files all passed. 0 … **Binary verified**: `rtk --version` prints `rtk 0.42.4`. `rtk ls` produces compact filtered direct… **Release build**: `cargo build --release` succeeded, release binary also runs and reports same ver…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 4 times, so the result is not a one-off.
What did not, or is not known
- Took 6 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
Of the 9 agentic-coding projects Argusic has installed and timed, rtk was the 8th fastest to reach a running state, and 8 of 9 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 6 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agentic-codingai-codinganthropicclaude-codeclicommand-line-toolcost-reductiondeveloper-toolsllmopen-sourceproductivityrusttoken-optimization
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/rtk)Questions
- Does rtk run?
- Yes. rtk runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test rtk?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 475f9ddfc20d. 4 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test rtk?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does rtk take to install?
- 6 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does rtk need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing rtk?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does rtk compare with the alternatives?
- Of the 9 agentic-coding projects Argusic has installed and timed, rtk was the 8th fastest to reach a running state, and 8 of 9 reached one at all.
- Where is the evidence for rtk?
- All 4 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.