#101 · Primary category: AI Gateway & API Infrastructure

NadirClaw

ai ai-cost-reduction ai-router claude-code codex cost-optimization gemini llm llm-gateway llm-proxy llm-router model-routing ollama openai openai-proxy openclaw prompt-routing proxy python self-hosted

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.

Project last updated:08/29/26

GitHub Stars

647

Forks

75

Contributors

13

License

Other

Why we included this project

Most coding sessions send plenty of trivial requests to expensive models, and NadirClaw sits in front of your tools to stop that. It classifies each prompt in about ten milliseconds, routes simple ones to cheap or local models, and only falls back to premium models when the cheap answer fails its own quality checks. Because it's a drop-in OpenAI-compatible proxy, Claude Code, Cursor, Codex, and similar tools just point at localhost and keep using your own API keys, with no third-party service in the path. The fallback chains and cost tracking hold up in daily use, and the published comparisons give you a concrete sense of the 40-70% savings before you commit. Teams watching their API spend climb will find it a low-friction way to cut costs without reworking their setup.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category