AI CacheKit

Lightweight caching library for AI/LLM API responses.
Reduce costs and improve performance by storing API responses locally with hash-based keys and optional TTL.

Features

• 🔹 Simple API: get, set
• 🔹 Local JSON storage (no external DB required)
• 🔹 Optional TTL (time-to-live) for cache expiration
• 🔹 Perfect for OpenAI, Anthropic, Ollama, etc.

Installation

From GitHub (development version):

pip install git+https://github.com/EDLadder/ai-cachekit.git

From PyPI (after release):

pip install ai-cachekit

Usage

from ai_cachekit import AIResponseCache

cache = AIResponseCache(backend="memory")
cache.set("question", "answer")
print(cache.get("question"))

File-Based Cache (JSON)

cache = AIResponseCache(backend="file", filepath="my_cache.json")
cache.set("key", "value")
print(cache.get("key"))

Redis Cache

cache = AIResponseCache(backend="redis", host="localhost", port=6379)
cache.set("key", "value")
print(cache.get("key"))

Why?

• Avoid repeated API calls (save cost & time)
• Minimal dependencies and setup
• Flexible for any AI API (OpenAI, LLaMA, etc.)

Development

Clone repo and install dev dependencies:

git clone https://github.com/EDLadder/ai-cachekit.git
cd ai-cachekit
pip install -r requirements.txt
pytest

Plans

• Support for Redis and SQLite backends.
• CLI tool for managing cache.
• Built-in stats: hit rate, saved cost estimation.
• Encryption for cached data.

License

MIT License – free to use and modify.