a16z-infra/llama2-chatbot

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1410 stars · 219 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Streamlit-based chatbot web app for chatting with LLaMA 2 models (7B, 13B, 70B) hosted on Replicate API endpoints. It includes per-session chat history, model hyperparameter configuration, Auth0 login, and a Dockerfile for deployment to Fly.io.

Use cases

• chat with llama 2 in a web interface
• self-host a llama2 chatbot app
• demo a large language model chatbot
• switch between llama2 7b 13b and 70b endpoints
• deploy a streamlit llm chat app with docker
• add auth0 login to a chatbot app

When to choose

• you want a ready-made web UI for chatting with LLaMA 2 via Replicate
• you need a quick demo or reference app for building LLM chatbots with Streamlit
• you want configurable model parameters and endpoint selection out of the box

When to avoid

• you need production-grade chat with persistent history - sessions clear on refresh
• you want to run models locally rather than through Replicate's paid API
• you need a framework or library to embed in your own app rather than a standalone demo
• you require an actively maintained project - it is a 2023 demo with no license

Facets

application · maturity maintenance

chatbot chat-interface llm-inference auth web-framework large-language-models chatbots artificial-intelligence web-development python self-hosted cross-platform streamlit llama2 replicate auth0 llm-chat demo-app docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="a16z-infra/llama2-chatbot")