Search

LLM application: 🖼️ Vision RAG

LLM application: 🩺 RAG Failure Diagnostics Clinic

LLM application: 🕸️ Knowledge Graph RAG with Citations

LLM application: 💾 AI ArXiv Agent with Memory

LLM application: 🛩️ AI Travel Agent with Memory

LLM application: 💬 Llama3 Stateful Chat

LLM application: 📝 LLM App with Personalized Memory

LLM application: 🗄️ Local ChatGPT Clone with Memory

LLM application: 🧠 Multi-LLM Application with Shared Memory

LLM application: 💬 Chat with GitHub (GPT & Llama3)

LLM application: 📨 Chat with Gmail

LLM application: 📄 Chat with PDF (GPT & Llama3)

LLM application: 📚 Chat with Research Papers (ArXiv) (GPT & Llama3)

LLM application: 📝 Chat with Substack

LLM application: 📽️ Chat with YouTube Videos

Reduce LLM API costs by 30-60% using TOON format

Reduce LLM API costs by 50-90% through intelligent context compression for AI agents (includes persistent memory & MCP support)

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Fully open reproduction of DeepSeek-R1

First-generation reasoning models from DeepSeek.