# rtk-ai/rtk

> A Rust CLI proxy that filters and compresses bash command output before it reaches the LLM context, cutting token usage by 60–90%. It hooks into Claude Code, Cursor, Gemini CLI and other agents.

- Magnitude: 3.1 out of 10 — Steady
- Stars: 84,934 total · +45 stars measured 2026-10-29, 00:05–10:00 UTC, ≈ 106 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Rust · License: Apache-2.0 · Created: 2026-01-22 · Last push: 2026-10-29
- GitHub: https://github.com/rtk-ai/rtk · Homepage: https://www.rtk-ai.app · Page: https://gitnova.dev/en/r/rtk-ai/rtk

## Useful for

- Cut token usage when a coding agent runs git, tests and builds
- Install the hook via rtk init -g so commands are auto-rewritten to rtk variants
- Check token savings statistics with rtk gain

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:05–10:00: 84889 → 84934 stars (+45). This is the change over that interval.
- Estimated end-of-day forecast: about +106 stars, using observed gains and the previous day.
- About 17 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 5,409
- Issues and pull requests: 4,717
- Watchers: 216
- Average over the last week: 109 per day
- Usual pace: 125 per day
- Latest release: dev-1.1.1-rc.584 (2026-10-29)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 70, 97, 114, 84, 94, 103, 107, 111, 165, 134, 175, 150, 117, 164, 112, 124, 137, 117, 114, 93, 95, 89, 134, 143, 105, 24, None, None, None, None

## Magnitude by day, last 14 days

10-16 4.0, 10-17 3.4, 10-18 3.5, 10-19 3.2, 10-20 3.1, 10-21 3.3, 10-22 3.1, 10-23 2.9, 10-24 2.8, 10-25 2.9, 10-26 2.9, 10-27 3.3, 10-28 3.4, 10-29 3.1

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 10:11 UTC, updated every 30 minutes.