VCAL Core — high-performance semantic cache and vector cache library for LLM applications.

in-memory semantic-search similarity-search hnsw vector-search semantic-cache llm-cache ai-infrastructure ai-cache vector-cache

• Updated Jul 5, 2026
• Rust

Decoupled, multi-tenant AI Traffic Manager and Governance Mesh for Enterprise GenAI runtimes.Designed for horizontal auto-scaling with multi-stage Docker builds and cross-cloud Terraform infrastructure blueprints (AWS ECS Fargate / Azure Container Apps / RDS PostgreSQL).

security zero-trust finops fastapi sqlmodel terraform-iac llm-gateway vector-cache

• Updated Jul 5, 2026
• Python

An Vector First Cache

cpp cache token-cache vector-cache pomaicache

• Updated Mar 5, 2026
• C++

Intelligent LLM router that dynamically routes prompts between local Ollama (Qwen) and cloud models (Gemini) using complexity scoring, semantic caching, and cost-aware decisioning.

devtools ai-agents cost-optimization gemini-api fastapi llm semantic-cache hybrid-ai local-llm llm-inference qwen ai-gateway llm-router llm-orchestration ai-infrastructure ai-tooling openai-compatible ollamma prompt-routing vector-cache

• Updated May 15, 2026
• Python

High-performance semantic vector cache for LLM queries in Python with Redis and cosine similarity deduplication

python redis embeddings cosine-similarity llm semantic-cache vector-cache

• Updated Nov 10, 2026
• Python

Chengeta AI is a unified memory and caching platform for AI agents, workflows, and autonomous systems.

caching embeddings autogen agno langchain crewai langgraph ai-memory llm-cache ai-infrastructure memory-layer agent-memory vector-cache

• Updated Jun 13, 2026
• Python

Ultra-low-latency in-memory vector cache engine in C with AVX2 SIMD, io_uring zero-copy networking, and circular overwrite ring buffer.

c99 io-uring vector-database in-memory-cache ann-search vector-cache simd-avx2

• Updated Sep 12, 2026
• C