by sodiumsun · Agent Tool · ★ 43
SnackCache Semantic caching proxy for OpenAI and Anthropic APIs. Stop paying for the same answer twice. Results • How It Works • Installation • Usage • Roadmap SnackCache is a caching layer for OpenAI and Anthropic APIs. It reduces your LLM API costs by caching responses and returning them for similar queries. Works with existing SDKs. No code changes beyond the base URL. The insight: Most developers use similar patterns - common system prompts, standard instructions, popular use cases.
| Stars | 43 |
| Forks | 1 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 75.0704135644576/100 |
| Last Updated | 2026-01-08 |
| Created | 2026-01-06 |
| Platforms | python |
| Est. Tokens | ~6k |
Explore other popular agent tool tools:
snackcache is Drop-in caching proxy for OpenAI and Anthropic APIs - stop paying for the same answer twice!. It is categorized as a Agent Tool with 43 GitHub stars.
snackcache is primarily written in Python. It covers topics such as anthropic, cache, llm.
You can find installation instructions and usage details in the snackcache GitHub repository at github.com/sodiumsun/snackcache. The project has 43 stars and 1 forks, indicating an active community.
snackcache is released under the MIT license, making it free to use and modify according to the license terms.