anpl-code/Deblank

A reversible code minifier for AI. Save tokens by stripping code format in your prompt, then perfectly restore it in the responces.

30
/ 100
Emerging

Deblank helps AI developers reduce the cost of using large language models (LLMs) for coding tasks. It takes human-readable source code (like Java, Python, C#) and removes non-essential formatting, significantly lowering the token count for LLM prompts. The LLM then processes this compact code, and Deblank restores its original, readable format in the response. This tool is for developers building AI-powered coding assistants, code generation tools, or similar LLM-driven applications.

Use this if you are a developer building LLM applications that process or generate code and need to optimize token usage and cost without sacrificing code readability or semantic accuracy.

Not ideal if you are working with natural language processing tasks that do not involve source code, or if your primary concern is not LLM token efficiency.

AI-powered coding LLM application development code optimization developer tools token efficiency
No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

18

Forks

Language

Python

License

MIT

Last pushed

Mar 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/anpl-code/Deblank"

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