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.
“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.”
| 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.
| 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.