Chat with local and cloud AI models. Query your own documents with RAG. All from the terminal.
Full conversation history with real-time streaming. Works with Ollama, OpenRouter, and NVIDIA NIM.
$ litemind-cli> What is RAG?RAG retrieves docs before answering, so you always see your latest data. No retraining needed.
Upload PDFs, Word docs, spreadsheets. Query with natural language.
$ litemind-cli rag Query: Security risks?[From 12 uploaded docs]• Injection attacks — top risk• Access control needs review
Switch between Ollama, OpenRouter, and NIM inline. No restart.
Providers: [Ollama] OpenRouter NIMModels: openai/gpt-5.6-luna-pro | ~anthropic/claude-fable-latest | deepseek/deepseek-v4-pro-0813Switch with Ctrl+1/2/3
Get up and running in under a minute.
LiteMind CLI is a terminal frontend for the LiteMindUI backend. It streams responses over SSE and supports RAG with multiple document formats.
Run the LiteMindUI backend via Docker or from source. It serves the REST API at localhost:8000.
Chat with AI models, upload documents for RAG, and switch providers inline - all without leaving your terminal.
LiteMind CLI is the terminal frontend for the LiteMindUI backend - a fullstack AI platform with REST API, Web UI, and Docker deployment.