What is RLAMA?

RLAMA is a complete AI platform that combines Retrieval-Augmented Generation (RAG) systems with intelligent agents, enabling users to build, deploy, and manage AI-powered solutions locally. It supports multiple document formats, advanced semantic chunking, and offers both CLI and visual interfaces for creating RAG systems. The platform also facilitates multi-agent orchestration with sequential, parallel, and hierarchical workflows.

How to use RLAMA?

Install RLAMA on macOS, Linux, or Windows. Use the CLI commands like 'rlama rag' to create a RAG system from documents, 'rlama agent' to create specialized agents, and 'rlama crew' to orchestrate multi-agent workflows. Alternatively, use the visual RAG builder to create RAG systems without coding. Start interactive sessions with 'rlama run' and manage systems with 'rlama list'.

Core features of RLAMA

Create and manage RAG systems with multiple document formats
Build specialized AI agents with roles and tools (RAG search, web search, code execution)
Orchestrate multi-agent crews with sequential, parallel, or hierarchical workflows
100% local processing for privacy
Interactive terminal sessions for chatting with RAG systems and agents
Visual RAG builder with drag-and-drop document upload
HTTP API server for integration
Cross-platform support (macOS, Linux, Windows)