Infrastructure●●Solid
AI Cost Firewall – OpenAI-compatible gateway with semantic caching
LLM gateway with Redis + Qdrant caching, but LiteLLM does this.
SlickShip It
vcaluser
113mo ago
Back to browse
GitHub Repository
Transparent, transport-layer semantic cache for LLM API calls, powered by Redis 8 Vector Sets.
2 starsPython
Khazad – Transparent Semantic Cache for LLM Calls on Redis Vector Sets
by guglielmoce·Jun 29, 2026·3 points·0 comments
AI Analysis
●●SolidBig BrainSlick
Transport-layer interception beats GPTCache with zero code changes required.
Strengths
- •Model-aware caching prevents gpt-4o answers serving gpt-4o-mini requests
- •Conversation-aware embedding uses full message history, not just last turn
- •Streaming support captures chunk-by-chunk for both sync and async clients
Weaknesses
- •Semantic caching tradeoffs may serve wrong answers for nuanced queries
- •Redis 8 Vector Sets requirement limits deployment options
Category
Target Audience
Developers building LLM-powered applications with high-volume repetitive queries
Similar To
GPTCache · CacheLLM · LLMCache
Similar Projects
Developer Tools●●Solid
Cachet – A drop-in semantic cache for LLM APIs, 100% local, in Rust
Semantic caching without a vector DB—just swap your base URL.
Big BrainShip It
Abhi_2112
506d ago
AI/ML●Mid
AI-Gateway – Open-source semantic caching proxy to reduce LLM API costs
Semantic caching proxy when Helicone and Portkey already dominate.
Ship It
arnab777
107d ago
AI/ML●●Solid
An agent that tunes its own cache
Two-tier caching saves real money, shown live on the dashboard.
Ship ItBig Brain
kaliades
701mo ago
Infrastructure●Mid
Nexus Gateway – Reduce LLM API Costs Using Semantic Caching
Semantic caching for LLM APIs exists (Anthropic prompt caching, Langchain, Miniplex, vLLM); gateway routing is table stakes.
Ship ItSolve My Problem
Sunnyanand_dev
213mo ago
AI/ML●●Solid
Self tuning chat exposing it's semantic and agentic cache
Tool result caching for agents when GPTCache and LangChain already do semantic caching.
Ship ItNiche Gem
kivanowbetterdb
4026d ago