Overview
rtk — Best for developers trying to reduce AI coding token costs.
rtk is a Rust CLI proxy designed to reduce LLM token consumption in common development commands, especially for Claude Code-style workflows.
GitHub monthly scan on 2026-05-19: 50483 stars, Rust, pushed on 2026-05-19. Created on 2026-01-22, it is a newer high-attention developer tool around AI coding cost control.
CLI proxy
Token optimization
Rust single binary
Claude Code workflow focus
Features & capabilities
Everything it does, in plain English.
The honest take
Where it shines, where it stumbles.
✓ Pros
- ✓Clear cost-saving problem
- ✓Single-binary Rust distribution
- ✓Relevant to AI coding power users
! Watch-outs
- !Actual savings depend on workflow
- !Proxy behavior should be tested before team rollout
Who it's for
Where rtk pays for itself fast.
Reduce token use in repetitive dev commands
Experiment with AI coding cost controls
Add a proxy layer to coding workflows
Community reviews
Share your take on rtk
Sign in to leave a verified review.
Alternatives
Similar tools worth comparing.
Supabase
Open-source backend-as-a-service with PostgreSQL database, auth, storage, and vector search for AI apps.
Hugging Face
The GitHub of machine learning — hosting 500,000+ AI models, datasets, and Spaces
Ollama
Run large language models locally on your Mac or Linux
OpenHands
AI-driven development agent for software engineering tasks.
GitHub MCP Server
GitHub's official MCP server for connecting agents to GitHub workflows.
Dify
Production-ready platform for building agentic AI workflows.