Last updated 08-11-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
RLAMA
RLAMA builds local RAG systems and multi-agent crews from your terminal on macOS, Linux, or Windows. You index folders of PDFs, Markdown, and code files, then query them through Ollama, OpenAI, or Hugging Face models without sending data to external servers. The open-source project also includes a visual RAG builder on rlama.dev.
Most RAG tools stop at document Q&A. RLAMA adds agent roles, tool wiring, and crew workflows so one terminal session can chain researchers, writers, and coders through sequential or parallel steps. Directory watching keeps RAG indexes fresh when files change, and an HTTP API exposes the same systems to other apps.
Developers building private knowledge bases, research teams indexing papers, and engineers who want offline document search use RLAMA for local embeddings and chunking. The project maintainers note active development is paused, but the open-source CLI and docs remain available for install.
CLI creates RAG indexes from folders with hybrid chunking defaults of 1000 tokens and 200 overlap
Supports 30+ file types including PDF, DOCX, Markdown, and common code extensions
Agent and crew commands assign roles like researcher, writer, and coder with RAG or web search tools
100% local processing option with Ollama so documents never leave your machine
Visual RAG builder on rlama.dev configures models, sources, and chunking without typing commands
Directory watch commands auto-index new files added to a watched folder
HTTP API server exposes RAG systems to other applications on a custom port
Open-source CLI with a no-code visual RAG builder on the website
Local Ollama processing keeps sensitive documents on your hardware
Agents, crews, and API server extend beyond basic document chat
Supports dozens of document and code file formats out of the box
Cross-platform installers for macOS, Linux, and Windows
Maintainers list the project as temporarily paused on the homepage
Enterprise integrations require the separate RLAMA-Pro sales plan
CLI-first workflow has a learning curve compared to hosted RAG SaaS
Advanced Snowflake and enterprise connectors are Pro-only features
What is RLAMA?
RLAMA is an open-source CLI and web platform for building Retrieval-Augmented Generation systems and AI agent crews on local hardware. You index documents, chat with them, and orchestrate multi-agent workflows from the terminal or a visual builder.
Is RLAMA free?
Yes. RLAMA is open source for personal use and free to install on macOS, Linux, and Windows. RLAMA-Pro is a separate enterprise offering with paid support and integrations that requires contacting sales.
Which models does RLAMA support?
RLAMA works with local Ollama models and also supports OpenAI and Hugging Face models. The visual builder lets you pick a model such as llama3.2 when creating a new RAG.
What file formats can RLAMA index?
RLAMA indexes text, Markdown, HTML, JSON, CSV, YAML, code files like Python and JavaScript, and documents including PDF, DOCX, PPTX, XLSX, and EPUB. The docs list more than 30 supported extensions.
Does RLAMA run fully offline?
Yes. RLAMA advertises 100% local processing when you use Ollama, meaning embeddings and queries stay on your machine with no data sent to external servers.
What are RLAMA agents and crews?
RLAMA agents are specialized roles with tools such as RAG search, web search, or code execution. Crews group multiple agents into sequential, parallel, or hierarchical workflows for tasks like research and content creation.
Is RLAMA still actively developed?
RLAMA's homepage states the project is temporarily paused because the maintainers are focused on full-time work and university studies. The open-source code, installer, and documentation remain available.