Ragbot

An AI-augmented brain assistant that combines large language models with Retrieval Augmented Generation

Open Source · MIT License

What is Ragbot?

Ragbot is an open source AI assistant that processes prompts along with your instructions, datasets, and runbooks to deliver context-aware, personalized responses that surpass out-of-the-box LLM capabilities.

Unlike generic AI assistants, Ragbot understands your specific context. Create folders containing customized dataset files for different use cases—personal life, work, education, or specific projects—and Ragbot adapts its responses accordingly.

Ragbot supports multiple LLM providers including OpenAI (GPT-4o, o1, o3), Anthropic (Claude Sonnet 4.5, Claude Opus 4.5), and Google (Gemini 2.5). Use the CLI for quick interactions or the Streamlit web interface for a richer experience.

Key Features

Multi-Provider LLM Support

Switch between OpenAI, Anthropic, and Google models. Use GPT-4o for one task, Claude for another, Gemini for a third—all from the same interface.

Retrieval Augmented Generation

RAG combines the power of pre-trained models with your personal knowledge base, resulting in responses that are more accurate, relevant, and grounded in your context.

Workspace Organization

Organize your context into instructions (who), runbooks (how), and datasets (what). Create separate workspaces for different domains of your life.

CLI and Web Interface

Use the command-line interface for quick interactions and scripting, or the Streamlit web UI for a more visual experience. Both share the same underlying capabilities.

Docker Deployment

Deploy with Docker for consistent, reproducible environments. One command gets you running with all dependencies configured.

Privacy-First Design

Your data stays yours. Keep sensitive context in a private repository while the application code remains open source.

Quick Start

Get Ragbot running in 5 minutes:

# Clone the repository git clone https://github.com/rajivpant/ragbot.git cd ragbot # Set up your API keys cp .env.docker .env # Edit .env and add at least one API key # Copy starter templates cp -r examples/templates/datasets/starter/ datasets/my-data/ cp examples/templates/instructions/starter/default-instructions.md instructions/ # Start with Docker docker-compose up -d # Access the web interface open http://localhost:8501

For detailed setup options including using your own data repository, see the full documentation on GitHub.

The Ragbot Ecosystem

Ragbot is part of a family of tools for AI-augmented knowledge work:

Use Case Recommendation
Quick setup, CLI-focused workflow Ragbot
Prefer Streamlit simplicity Ragbot
Need advanced RAG with vector search RaGenie
Need microservices architecture RaGenie
Want both CLI and modern web UI Use both!

RaGenie is the next-generation sibling to Ragbot, offering a microservices architecture with automatic embeddings, semantic search, and a modern React frontend. Both products share the same data layer and continue to be actively developed.

Resources