zilliztech/GPTCache

semantic cache for LLM queries, speeds up GPT apps, cuts API costs

speeds up LLMs with fast key-value caching
LMCache/LMCache
a fast, simple key-value cache
tidwall/pogocache
Redis-compatible cache store with sub-300 microsecond latency
microsoft/garnet
open-weight GPT models for reasoning and agent tasks
openai/gpt-oss
fastRAG helps you build efficient retrieval-augmented generation pipelines with optimized LLMs and search tools
IntelLabs/fastRAG
open source status page for incidents and outages
cachethq/cachet
1-bit LLM inference on CPUs and GPUs with BitNet
microsoft/BitNet
Benchmark for LLMs on software engineering tasks
openai/SWELancer-Benchmark
scans LLMs for vulnerabilities like prompt injection, hallucination, and data leaks
NVIDIA/garak
Open-source platform for evaluating and optimizing LLM apps
comet-ml/opik