rtk-ai/rtk
CLI proxy reducing LLM token usage for AI coding agents
- Chart
- Not on a chart right now
- Stars
- 87.2k
What it is
A single, zero-dependency Rust binary that compresses common development command outputs to cut LLM token consumption by 60-90%. It integrates with 18 AI coding tools including Claude Code, Cursor, and Gemini CLI with no workflow changes.
Who it is for
Developers using AI coding agents who want to reduce token costs and context bloat from verbose command outputs.
Why it is trending
Following its v1.2.0 release in November 2026, it gained 155 stars today and has reached 87,151 total stars. It stands out by filtering over 100 dev commands in under 25 ms with a single Rust binary while offering customizable pipelines.
Main features
- Compresses outputs of 100+ dev commands in under 25 ms
- Tracks daily and session token savings via rtk gain
- Supports pipelines for compressing reads and routing to cheaper models
- Integrates with 18 AI coding tools via hooks, plugins, or rules files
Summarized on November 19, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary