High-performance chatbot powered by Groq LPU
A stateful AI agent delivering near-instant responses (500+ tokens/sec). It solves latency issues by offloading inference to Groq infrastructure.
LangGraph memory persistence.
Integrated Tavily web access.
# Clone and install
$ git clone [private-repo]
$ pip install -r requirements.txt
# Environmental Variables
GROQ_API_KEY=your_key
TAVILY_API_KEY=your_key
Released under the MIT License. Open for modification and scaling.