doramirdor/NadirClaw

Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

57
/ 100
Established

This project helps developers and AI application builders reduce their spending on large language model (LLM) APIs. It intelligently routes prompts to the most cost-effective model, sending simple requests to cheaper models and complex ones to premium services. The tool acts as a local proxy, taking in LLM prompts and outputting responses while minimizing API costs, ideal for anyone running frequent LLM calls or AI agents.

286 stars. Available on PyPI.

Use this if you are developing or running AI applications and want to automatically optimize your LLM API costs by routing prompts to different models based on their complexity.

Not ideal if you only use LLMs for very occasional, simple tasks and cost optimization isn't a primary concern.

AI application development LLM cost management developer tools API optimization AI agent orchestration
Maintenance 10 / 25
Adoption 10 / 25
Maturity 20 / 25
Community 17 / 25

How are scores calculated?

Stars

286

Forks

36

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Dependencies

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/doramirdor/NadirClaw"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.