ashishpatel26/omnicache-ai
Unified multi-layer caching library for AI/agent pipelines — LangChain, LangGraph, AutoGen, CrewAI, Agno, A2A
Supports semantic caching with cosine similarity matching across five specialized layers (LLM responses, embeddings, retrieval, context, and semantic), plus tag-based invalidation for bulk eviction. Provides adapter hooks for six frameworks (LangChain, LangGraph, AutoGen, CrewAI, Agno, A2A) and middleware wrappers for any callable, backed by pluggable storage (in-memory LRU, disk, Redis, FAISS, ChromaDB) with unified TTL and eviction policies.
Available on PyPI.
Stars
15
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 26, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ashishpatel26/omnicache-ai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
thedotmack/claude-mem
A Claude Code plugin that automatically captures everything Claude does during your coding...
Open-Source-Legal/OpenContracts
Humans and AI agents, building knowledge bases together. Self-hosted document annotation,...
omega-memory/omega-memory
Persistent memory for AI coding agents
volcengine/MineContext
MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）
gengxy1216/FlockMem
✦ FlockMem is a lightweight, local-first long-term collective memory bus for multi-agents,...