Claude Code model router
Rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Install
brew install rtk # macOS / LinuxFound in the project README. Check it for setup steps after installing.
git clone https://github.com/rtk-ai/rtk.gitFrom the README
Agent-agnostic token optimization: compress, route, filter, and more. One composable pipeline across everything your AI agent reads and sends — built on RTK's battle-tested bash-output compression (up to 90% smaller). Website • Install • Troubleshooting • Architecture • Discord English • Francais • 中文 • 日本語 • 한국어 • Espanol • Português rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, 100+ supported commands, Full explanation: How RTK Savings Work Installation Then check you have the right package — another project named "rtk" exists on crates.io: Cargo, pre-built binaries, native Windows, WSL, and uninstall: Installation guide What You Install RTK ships as three downloads. The two rtk editions install a binary with the same name — hooks, scripts and agent config work unchanged across both — so they cannot be installed together. Uninstall one before installing the other. Production use is free, engine and daemon included. What the BUSL grant does not cover is offering RTK or a derivative to third parties as a commercial product or service — for that, contact contact@rtk-ai.app. What the Apache-2.0 edition omits and where the licence boundary falls: Editions and Licensing Quick Start The agent receives compact output without ever calling rtk explicitly. The hook only fires on Bash tool calls. Built-in tools like Read, Grep and Glob do not pass through it. Use shell commands (cat, rg, find) or call rtk read, rtk grep, rtk find directly. Per-agent setup, --dry-run, and uninstall: Quick Start · Supported Agents How It Works Four strategies applied per command type: 1. Smart Filtering - Removes noise (comments, whitespace,…
Details
- Repository
- rtk-ai/rtk
- Website
- www.rtk-ai.app
- Language
- Rust
- License
- Apache-2.0
- Last updated
- 3 November 2026
- Topics
- agentic-codingai-codinganthropicclaude-codeclicommand-line-toolcost-reductiondeveloper-toolsllmopen-sourceproductivityrust
- Listed in
- subinium/awesome-claude-code
FAQ
What is Rtk?
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies It is a model router for Claude Code, from rtk-ai/rtk on GitHub.
How do I install Rtk?
Run brew install rtk # macOS / Linux, then follow the setup in the README.
Is Rtk popular?
rtk-ai/rtk has 85,448 GitHub stars and 5,473 forks, and is included in 1 curated Claude Code list. It was last updated on 3 November 2026.
More model routers & proxies
Claude Code Router
38kmusistudio/claude-code-router
Routes Claude Code requests to different models and providers based on rules you configure.
Headroom
79kheadroomlabs-ai/headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
CLIProxyAPI
57krouter-for-me/CLIProxyAPI
Proxy that exposes subscription-based CLIs as OpenAI, Gemini or Claude compatible APIs usable by Claude Code.
Caveman
117kJuliusBrussee/caveman
why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
CC Switch
152kfarion1231/cc-switch
Cross-platform desktop app for switching Claude Code providers, configs and MCP servers.
OmniRoute
84kcheaper-inference/OmniRoute
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
Browse the most popular Claude Code mods, all model routers & proxies, or the skills and MCP server directories.