vcache-project/vCache

Reliable and Efficient Semantic Prompt Caching with vCache

36
/ 100
Emerging

Implements online-learned decision boundaries for semantic similarity detection, eliminating manual threshold tuning while guaranteeing user-specified error rate bounds. Sits between application servers and LLM backends (OpenAI, Anthropic, or on-prem models), using embedding-based similarity matching with pluggable vector databases (HNSWLib), eviction policies (FIFO, LRU, MRU, SCU), and similarity evaluators. Provides modular configuration to swap inference engines, embedding models, and storage backends for RAG pipelines, agentic systems, and database-driven LLM workloads.

No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 7 / 25

How are scores calculated?

Stars

60

Forks

3

Language

Python

License

Last pushed

Dec 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/vcache-project/vCache"

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