AI in your terminal.

Chat with local and cloud AI models. Query your own documents with RAG. All from your terminal.

user@litemind ~ $

$ litemind-cli

_ _ _ __ __ _ _ ____ _ ___

| | (_) |_ ___| \/ (_)_ __ __| | / ___| | |_ _|

| | | | __/ _ \ |\/| | | '_ \ / _` | | | | | | |

| |___| | || __/ | | | | | | | (_| | | |___| |___ | |

|_____|_|\__\___|_| |_|_|_|_|\__,_| \____|_____|___|

Terminal interface for LiteMindUI · Chat · RAG

$ litemind-cli status

✓ Backend healthy — http://localhost:8000

✓ Provider ollama — llama3.2:latest

✓ RAG ready — 3 documents indexed

1 chat · 2 rag · 3 settings · q quit

Features

Everything the backend serves, in three tabs: chat, RAG, and settings.

Full conversation history with real-time token streaming. Works with Ollama, OpenRouter, and NVIDIA NIM.

> What is RAG?

RAG retrieves your docs before answering —
fresh data, no retraining needed.

Upload PDFs, Word docs, spreadsheets. Ask questions in plain language.

$ litemind-cli rag
Query: Security risks?

• Injection attacks — top risk
• Access control needs review

Ollama, OpenRouter, and NVIDIA NIM out of the box. Change provider and model any time in Settings. No restart needed.

ollamaopenrouternim

Up and running in under a minute.

user@litemind ~ $

$ pip install litemind-cli

# Start the backend (Docker)

$ curl -fsSL https://raw.githubusercontent.com/debabratamishra/litemind-ui/main/install.sh | bash

# Launch the TUI

$ litemind-cli

# Check connectivity

$ litemind-cli status

LiteMind CLI is the terminal frontend for the LiteMindUI backend, streaming responses over SSE and running RAG on your own documents.

Run LiteMindUI via Docker or from source. It serves the REST API at localhost:8000.

Install from PyPI or build from source, then launch with litemind-cli.

Chat with models, upload documents for RAG, and switch providers — without leaving the terminal.

LiteMind CLI is the terminal frontend for the LiteMindUI backend — a fullstack AI platform with a REST API, web UI, and Docker deployment.