← All comparisons
Supported directly, then measured

What LemonCrow uses rtk for, and what it adds on top.

rtk hooks Bash tool calls and rewrites commands like git status, cat, and pytest to compact equivalents. LemonCrow auto-detects it and shells out to it for a safe, read-only allowlist, on top of its own in-process cat/grep/find compaction.

What rtk says about itself
“CLI proxy that reduces LLM token consumption by 60-90% on common dev commands.”
“Estimates based on medium-sized TypeScript/Rust projects. Actual savings vary by project size.”
Supported directly -- soft auto-detect, no config needed ~69.6k stars -- largest tool in this whole comparison set ↗ Publishes some numbers ...never against a real coding task, or another tool
rtk's own published table -- estimated tokens per command, "medium-sized TypeScript/Rust project"
Operation Standard (est.) rtk (est.) Savings
ls / tree 2,000 400 -80%
cat / read 40,000 12,000 -70%
grep / rg 16,000 3,200 -80%
git status 3,000 600 -80%
cargo test / npm test 25,000 2,500 -90%
Total (12 operation types) ~118,000 ~23,900 -80%

5 of 12 published rows shown -- full table at the source link above.

What LemonCrow measured instead
Method Accuracy control Result
rtk: per-command estimate, one stated project profile None -- no task run, no correctness checked -80% avg (self-reported)
★ LemonCrow: Terminal-Bench 2.1, 89 real agentic tasks 78.7% vs. 78.9% expected (-0.2pp, held flat) -28.1% cost, real tasks

rtk's table is an estimate on one stated project shape -- no task run, no accuracy check. Terminal-Bench: -28.1% cost, accuracy checked against a public leaderboard. Note: rtk's rewrite hook only fires on Bash calls -- Read/Grep/Glob bypass it unless called via rtk read/rtk grep.

The true story

rtk is the most-starred tool in this comparison. LemonCrow auto-detects it, no config needed, and checks its own layer against a real leaderboard instead of a stated project profile.