RLAMA
The complete AI platform for creating RAG systems and intelligent agents. Build, deploy, and manage AI-powered solutions with local models - from document Q&A to autonomous agent crews.
Project Currently Paused: This project is temporarily on hold due to our current commitments with full-time work and university studies. We're unable to dedicate time to active development at the moment, but we plan to resume when our schedule allows.
Available for macOS, Linux, and Windows
$ rlama --version
RLAMA v0.1.29
$ rlama rag llama3 documentation ./docs
Generating embeddings
Embeddings generated successfully!
RAG system "documentation" created successfully!
$ rlama agent create researcher --role="Data Analyst"
Agent "researcher" created with RAG search tools!
$ rlama crew create research-team researcher writer
Crew "research-team" ready for collaborative tasks!
What is RLAMA?
A complete AI platform that combines RAG systems with intelligent agents, creating powerful automated workflows for any task - from document analysis to complex multi-agent collaboration.
Complete RAG Solution
Create, manage, and interact with Retrieval-Augmented Generation systems tailored to your documentation.
- Multiple document formats (.txt, .md, .pdf, etc.)
- Advanced semantic chunking strategies
- Local storage and processing with no data sent externally
AI Agents & Crews
Create specialized AI agents that can perform specific tasks or collaborate as crews to solve complex problems.
- Multiple agent roles (researcher, writer, coder, analyst)
- Agent tools (RAG search, code execution, web search)
- Collaborative workflows with sequential or parallel steps
Multi-Agent Orchestration
Orchestrate multiple agents working together in sophisticated workflows for complex automation tasks.
- Sequential workflows for step-by-step processes
- Parallel execution for concurrent task processing
- Hierarchical delegation with manager agents
Flexible Integration
Adapt RLAMA to your workflow with multiple integration options and extensive tooling support.
- HTTP API server for application integration
- Cross-platform support (macOS, Linux, Windows)
- OpenAI model support alongside Ollama
Key Features
Everything you need to build powerful RAG systems and intelligent AI agent workflows
RAG Systems
Create and manage Retrieval-Augmented Generation systems with multiple document formats.
AI Agents & Crews
Build specialized AI agents that collaborate as crews to solve complex problems.
Local Processing
100% local processing with no data sent to external servers for maximum privacy.
Intelligent Automation
Automate workflows with AI agents equipped with tools and collaborative capabilities.
Multi-Agent Workflows
Orchestrate multiple agents working together in sequential or parallel workflows.
Interactive Sessions
Chat with your RAG systems and agents through intuitive terminal interfaces.
Visual RAG Builder
Create powerful RAG systems in minutes without writing a single command
Create RAGs visually in 2 minutes
No coding required. Our intuitive interface makes RAG creation accessible to everyone.
- Easy drag-and-drop document upload
- Configure advanced settings with simple controls
- Save and share your configurations
my-rag
Choose a name for your new RAG
Model
llama3.2
Ollama, OpenAI, or Hugging Face models
Source Type
Local Folder
Website
Source Configuration
Configure local folder source
Local Folder Path
./documents
Path to your document folder
Exclude Directories
node_modules,dist
Exclude Extensions
.log,.tmp
Process Extensions
.md,.py,.js
Chunking Settings
Controls document splitting
Strategy
Hybrid
Chunk Size
1000
Chunk Overlap
200
RLAMA in Action
See how simple it is to create and use RAG systems with our intuitive CLI
Create a RAG System
Index a folder of documents to create a new RAG system. Supports multiple file formats and embedding models.
> Create a new RAG system named "documentation" using the llama3 model
> and indexing all documents in the ./docs folder
rlama rag llama3 documentation ./docs
Popular Use Cases
Discover how RLAMA powers both RAG systems and AI agent workflows
- Technical Documentation: Query your project documentation, manuals, and specifications with intelligent RAG systems.
- Private Knowledge Base: Create secure RAG systems for sensitive documents with full privacy and local processing.
- Research Assistant: Deploy AI agents to query research papers, analyze data, and generate insights.
- AI Agent Workflows: Create specialized agents for coding, writing, analysis, and other automated tasks.
- Content Creation Crews: Orchestrate teams of AI agents for content creation, review, and publishing workflows.
- Automated Workflows: Build complex multi-step workflows with agents working in sequence or parallel.
Command Reference
A complete reference of all available commands to master RLAMA
rag
Create a new RAG system from documents
rlama rag [model] [rag-name] [folder-path]
agent
Create and manage AI agents with specific roles
rlama agent [create|run|list] [agent-name] [options]
crew
Create and orchestrate multi-agent crews for complex tasks
rlama crew [create|run|list] [crew-name] [agents...]
run
Start an interactive session with a RAG system or agent
rlama run [rag-name|agent-name|crew-name]
list
List all available RAG systems, agents, and crews
rlama list [--type=rag|agents|crews]
Exploring RAG for your projects?
We'd be happy to share some insights on how RAG technology can be applied to different use cases and answer any questions you might have.
Common Issues & Solutions
Quick fixes for the most frequently encountered problems
Ollama not accessible
Text extraction problems
RAG not finding relevant information
Supported File Formats
RLAMA supports a wide variety of document formats to meet all your needs
Text
- .txt
- .md
- .html
- .json
- .csv
- .yaml
- .yml
- .xml
Code
- .go
- .py
- .js
- .java
- .c
- .cpp
- .cxx
- .h
- .rb
- .php
- .rs
- .swift
- .kt
- .ts
- .f
- .F
- .F90
- .el
- .svelte
Documents
- .docx
- .doc
- .rtf
- .odt
- .pptx
- .ppt
- .xlsx
- .xls
- .epub
Ready to streamline your document question-answering?