Skip to main content
ClaudeWave

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Tools73.6k stars4.6k forksRustApache-2.0Updated today
Editor's note

RTK is a CLI proxy written in Rust that intercepts shell commands invoked by AI coding agents and compresses their output before it reaches the model's context window. It supports over 100 commands including `git status`, `git diff`, `cargo test`, `pytest`, `grep`, `ls`, `cat`, and `docker ps`, applying four strategies per command: smart filtering to strip noise and boilerplate, grouping of similar items such as files by directory, truncation of verbose output, and format normalization. Integration with Claude Code is handled through a Bash hook installed via `rtk init -g`, which automatically rewrites qualifying shell calls to route through RTK; the agent receives only the compressed output without any explicit changes to its prompts. According to the project's own benchmarks on a medium-sized TypeScript/Rust project, a 30-minute Claude Code session drops from roughly 118,000 tokens to about 23,900 tokens, an 80 percent reduction, with test runners like `pytest` and `go test` achieving up to 90 percent savings. The tool ships as a single static binary with no runtime dependencies, adds under 10 milliseconds of overhead, and is installable via Homebrew. Developers paying per-token API costs or hitting context limits during agentic coding sessions are the primary audience.

ClaudeWave Trust Score
100/100
Verified
Passed
  • Open-source license (Apache-2.0)
  • Actively maintained (<30d)
  • Healthy fork ratio
  • Clear description
  • Topics declared
  • Documented (README)
Last scanned: 6/11/2026
Get started
Method: Clone
Terminal
git clone https://github.com/rtk-ai/rtk
1. Clone the repository.
2. Follow the README for installation and usage instructions.
Use cases

Tools overview

<p align="center">
  <img src="https://avatars.githubusercontent.com/u/258253854?v=4" alt="RTK - Rust Token Killer" width="500">
</p>

<p align="center">
  <strong>High-performance CLI proxy that cuts up to 90% of the bash output your agent reads</strong>
</p>

<p align="center">
  <a href="https://github.com/rtk-ai/rtk/actions"><img src="https://github.com/rtk-ai/rtk/workflows/Security%20Check/badge.svg" alt="CI"></a>
  <a href="https://github.com/rtk-ai/rtk/releases"><img src="https://img.shields.io/github/v/release/rtk-ai/rtk" alt="Release"></a>
  <a href="https://opensource.org/licenses/Apache-2.0"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License: Apache 2.0"></a>
  <a href="https://discord.gg/RySmvNF5kF"><img src="https://img.shields.io/discord/1470188214710046894?label=Discord&logo=discord" alt="Discord"></a>
  <a href="https://formulae.brew.sh/formula/rtk"><img src="https://img.shields.io/homebrew/v/rtk" alt="Homebrew"></a>
</p>

<p align="center">
  <a href="https://www.rtk-ai.app">Website</a> &bull;
  <a href="#installation">Install</a> &bull;
  <a href="https://www.rtk-ai.app/guide/troubleshooting">Troubleshooting</a> &bull;
  <a href="docs/contributing/ARCHITECTURE.md">Architecture</a> &bull;
  <a href="https://discord.gg/RySmvNF5kF">Discord</a>
</p>

<p align="center">
  <a href="README.md">English</a> &bull;
  <a href="README_fr.md">Francais</a> &bull;
  <a href="README_zh.md">中文</a> &bull;
  <a href="README_ja.md">日本語</a> &bull;
  <a href="README_ko.md">한국어</a> &bull;
  <a href="README_es.md">Espanol</a> &bull;
  <a href="README_pt.md">Português</a>
</p>

---

rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, 100+ supported commands, <10ms overhead.

## What RTK Does

RTK intercepts shell commands and compresses their output before your agent reads it.

| Operation | What RTK does to the output |
|-----------|-----------------------------|
| `ls` / `tree` | Tree format with file counts instead of one line per entry |
| `cat` / `read` | Smart file reading: signatures and structure over full bodies |
| `grep` / `rg` | Truncates long lines, groups matches by file |
| `git status` | Compact stat format, grouped by state |
| `git diff` | Reduced context, headers stripped |
| `git log` | Hash, author and subject only |
| `git add/commit/push` | Confirmation line instead of full progress output |
| `cargo test` / `npm test` | Failures only, passing tests collapsed to a count |
| `ruff check` | Grouped by rule and file |
| `pytest` | Failures only, traceback trimmed |
| `go test` | NDJSON parsed, failures only |
| `docker ps` | Essential fields only |

## How Savings Work

RTK cuts **up to 90% of the bash output** your agent reads. That is what RTK measures, and it is not the same as cutting your bill by 90%.

Bash output is **one contributor to input tokens**, alongside your prompt, the system prompt and conversation history. Input tokens are in turn **only part of the bill**, which also counts output tokens. The reduction dilutes at every step.

The token counts RTK reports are estimated as `bytes / 4` — RTK ships no tokenizer, so the **percentages are reliable but the absolute token numbers are approximate**.

> Full explanation: [How RTK Savings Work](docs/guide/resources/savings-explained.md)

## Installation

### Homebrew (recommended)

```bash
brew install rtk
```

### Quick Install (Linux/macOS)

```bash
curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh
```

> Installs to `~/.local/bin`. Add to PATH if needed:
> ```bash
> echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc  # or ~/.zshrc
> ```

### Cargo

```bash
cargo install --git https://github.com/rtk-ai/rtk
```

### Pre-built Binaries

Download from [releases](https://github.com/rtk-ai/rtk/releases):
- macOS: `rtk-x86_64-apple-darwin.tar.gz` / `rtk-aarch64-apple-darwin.tar.gz`
- Linux: `rtk-x86_64-unknown-linux-musl.tar.gz` / `rtk-aarch64-unknown-linux-gnu.tar.gz`
- Windows: `rtk-x86_64-pc-windows-msvc.zip`

> **Windows users**: Extract the zip and place `rtk.exe` somewhere in your PATH (e.g. `C:\Users\<you>\.local\bin`). Run RTK from **Command Prompt**, **PowerShell**, or **Windows Terminal** — do not double-click the `.exe` (it will flash and close). The full hook system works natively on Windows (and in [WSL](https://learn.microsoft.com/en-us/windows/wsl/install)). See [Windows setup](#windows) below for details.

### Verify Installation

```bash
rtk --version   # Should show "rtk 0.28.2"
rtk gain        # Should show the savings dashboard
```

> **Name collision warning**: Another project named "rtk" (Rust Type Kit) exists on crates.io. If `rtk gain` fails, you have the wrong package. Use `cargo install --git` above instead.

## Quick Start

```bash
# 1. Install for your AI tool
rtk init -g                     # Claude Code / Copilot (default)
rtk init -g --gemini            # Gemini CLI
rtk init -g --codex             # Codex (OpenAI)
rtk init -g --agent cursor      # Cursor
rtk init -g --agent windsurf    # Windsurf
rtk init --agent cline          # Cline / Roo Code
rtk init --agent kilocode       # Kilo Code
rtk init --agent antigravity    # Google Antigravity
rtk init --agent kimi           # Kimi AI
rtk init -g --agent pi          # Pi
rtk init --agent hermes         # Hermes
rtk init -g --agent droid       # Factory Droid

# 2. Restart your AI tool, then test
git status  # Automatically rewritten to rtk git status
```

Hook-based agents rewrite Bash commands (e.g., `git status` -> `rtk git status`) before execution. Plugin-based agents, including Hermes, use their plugin API to rewrite commands before execution. The agent receives compact output without needing to call `rtk` explicitly.

**Important:** the hook only runs on Bash tool calls. Claude Code built-in tools like `Read`, `Grep`, and `Glob` do not pass through the Bash hook, so they are not auto-rewritten. To get RTK's compact output for those workflows, use shell commands (`cat`/`head`/`tail`, `rg`/`grep`, `find`) or call `rtk read`, `rtk grep`, or `rtk find` directly.

## How It Works

```
  Without rtk:                                    With rtk:

  Claude  --git status-->  shell  -->  git         Claude  --git status-->  RTK  -->  git
    ^                                   |            ^                      |          |
    |         full raw output           |            |  compact output      | filter   |
    +-----------------------------------+            +------- (filtered) ---+----------+
```

Four strategies applied per command type:

1. **Smart Filtering** - Removes noise (comments, whitespace, boilerplate)
2. **Grouping** - Aggregates similar items (files by directory, errors by type)
3. **Truncation** - Keeps relevant context, cuts redundancy
4. **Deduplication** - Collapses repeated log lines with counts

## Commands

> Percentages below are **reductions in bash output**, not reductions in your bill. See [How Savings Work](#how-savings-work).

### Files
```bash
rtk ls .                        # Compact directory tree
rtk read file.rs                # Smart file reading
rtk read file.rs -l aggressive  # Signatures only (strips bodies)
rtk smart file.rs               # 2-line heuristic code summary
rtk find "*.rs" .               # Compact find results
rtk grep "pattern" .            # Grouped search results
rtk diff file1 file2            # Condensed diff (exit 1 if files differ)
```

### Git
```bash
rtk git status                  # Compact status
rtk git log -n 10               # One-line commits
rtk git diff                    # Condensed diff
rtk git add                     # -> "ok"
rtk git commit -m "msg"         # -> "ok abc1234"
rtk git push                    # -> "ok main"
rtk git pull                    # -> "ok 3 files +10 -2"
```

### GitHub CLI
```bash
rtk gh pr list                  # Compact PR listing
rtk gh pr view 42               # PR details + checks
rtk gh issue list               # Compact issue listing
rtk gh run list                 # Workflow run status
```

### Test Runners
```bash
rtk jest                        # Jest compact (failures only)
rtk vitest                      # Vitest compact (failures only)
rtk playwright test             # E2E results (failures only)
rtk pytest                      # Python tests (-90%)
rtk go test                     # Go tests (NDJSON, -90%)
rtk cargo test                  # Cargo tests (-90%)
rtk rake test                   # Ruby minitest (-90%)
rtk rspec                       # RSpec tests (JSON, -60%+)
rtk err <cmd>                   # Filter errors only from any command
rtk test <cmd>                  # Generic test wrapper - failures only (-90%)
```

### Build & Lint
```bash
rtk lint                        # ESLint grouped by rule/file
rtk lint biome                  # Supports other linters
rtk tsc                         # TypeScript errors grouped by file
rtk next build                  # Next.js build compact
rtk prettier --check .          # Files needing formatting
rtk cargo build                 # Cargo build (-80%)
rtk cargo clippy                # Cargo clippy (-80%)
rtk ruff check                  # Python linting (JSON, -80%)
rtk golangci-lint run           # Go linting (JSON, -85%)
rtk rubocop                     # Ruby linting (JSON, -60%+)
rtk sbt test                    # ScalaTest output (-90%)
rtk sbt compile                 # Compilation errors only (-75%)
rtk sbt run                     # Strip SBT preamble noise
```

### Package Managers
```bash
rtk pnpm list                   # Compact dependency tree
rtk uv run pytest               # Preserve uv env, keep program output
rtk pip list                    # Python packages (auto-detect uv)
rtk pip outdated                # Outdated packages
rtk bundle install              # Ruby gems (strip Using lines)
rtk prisma generate             # Schema generation (no ASCII art)
```

### AWS
```bash
rtk aw
agentic-codingai-codinganthropicclaude-codeclicommand-line-toolcost-reductiondeveloper-toolsllmopen-sourceproductivityrusttoken-optimization

What people ask about rtk

What is rtk-ai/rtk?

+

rtk-ai/rtk is tools for the Claude AI ecosystem. CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies It has 73.6k GitHub stars and was last updated today.

How do I install rtk?

+

You can install rtk by cloning the repository (https://github.com/rtk-ai/rtk) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is rtk-ai/rtk safe to use?

+

Our security agent has analyzed rtk-ai/rtk and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains rtk-ai/rtk?

+

rtk-ai/rtk is maintained by rtk-ai. The last recorded GitHub activity is from today, with 1757 open issues.

Are there alternatives to rtk?

+

Yes. On ClaudeWave you can browse similar tools at /categories/tools, sorted by popularity or recent activity.

Deploy rtk to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: rtk-ai/rtk
[![Featured on ClaudeWave](https://claudewave.com/api/badge/rtk-ai-rtk)](https://claudewave.com/repo/rtk-ai-rtk)
<a href="https://claudewave.com/repo/rtk-ai-rtk"><img src="https://claudewave.com/api/badge/rtk-ai-rtk" alt="Featured on ClaudeWave: rtk-ai/rtk" width="320" height="64" /></a>

More Tools

rtk alternatives