Add llm-token-surgeon to Natural Language Processing

[ashishjsharda]

Project

llm-token-surgeon

Checklist

• One project per PR
• PR title format: Add llm-token-surgeon
• Entry format: - [llm-token-surgeon](url) - A CLI and Python library that reduces LLM API token usage by 30-70% through prompt optimization, redundancy removal, and semantic compression.
• Description is concise and short

Why This Project Is Awesome

Which criterion does it meet? (pick one)

• Industry Standard - The go-to tool for a specific use case
• Rising Star - 5000+ stars in < 2 years, significant adoption
• Hidden Gem - Exceptional quality, solves niche problems elegantly

Explain:

llm-token-surgeon solves a universal and costly pain point — LLM API token waste. Most teams unknowingly burn 40–70% of their token budget on redundant instructions and bloated prompts. This tool reduces that by 30–70% with zero accuracy loss, works as a drop-in CLI or Python middleware, and supports OpenAI, Anthropic, and Gemini out of the box.

How It Differs

No other entry in awesome-python focuses specifically on LLM prompt optimization and token cost reduction. Existing NLP libraries focus on parsing and analysis — this is the only tool purpose-built to reduce API spend while preserving output quality.

[JinyangWang27]

@ashishjsharda Thanks for your submission. However, this project does not meet our acceptance criteria:

Repository age: The repository was created 4 hours ago. We require a minimum of 3 months (or 6 months for Hidden Gem submissions) to ensure project stability.

GitHub stars: 0 star (minimum 100 required, or strong justification for Hidden Gem).

Please see our CONTRIBUTING.md for full requirements. You're welcome to resubmit once the project has matured and gained community traction.