Skip to content

[GitHub Trending] rtk-ai/rtk

9.5 relevance
Score Breakdown
technical depth
8
novelty
9
actionability
9
community
8
strategic
7
personal
10

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

CLI proxy slashes LLM token costs, highly actionable and novel.

2026-05-19 ai/ml GitHub Trending
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies - rtk-ai/rtk
Summary

rtk, a single Rust binary with <10ms overhead, hooks into AI coding tools (Claude Code, Copilot, Gemini CLI) to intercept bash commands and apply filtering, grouping, truncation, and deduplication, cutting LLM token consumption by 60-90% across 100+ commands. In a 30-minute Claude Code session, it reduced total tokens from ~118,000 to ~23,900, with commands like git add/commit/push seeing 92% savings. Open-source on GitHub, it uses hook-based or plugin-based rewriting for seamless integration.

Key Takeaway

Install rtk as a local CLI proxy to your AI coding tools to automatically compress command outputs and achieve ~80% token savings on common workflows.

Why it matters

For engineers building AI-assisted development pipelines, rtk directly reduces token costs and latency by preprocessing shell output before it enters LLM context, making agent loops more efficient and cheaper.

Full Article

High-performance CLI proxy that reduces LLM token consumption by 60-90% Website • Install • Troubleshooting • Architecture • Discord English • Francais • 中文 • 日本語 • 한국어 • Espanol rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, 100+ supported commands, <10ms overhead. Token Savings (30-min Claude Code Session) Operation Frequency Standard rtk Savings ls / tree 10x 2,000 400 -80% cat / read 20x 40,000 12,000 -70% grep / rg 8x 16,000 3,200 -80% git status 10x 3,000 600 -80% git diff 5x 10,000 2,500 -75% git log