workflowstacks
mcp-server

nosia: AI RAG Platform

Get a self-hosted AI RAG + MCP platform with nosia. For startup founders needing all-in-one solutions.
212 stars19 forksRubyGuide quality 8/10Updated 8/9/2026100% free · open source
What it does

Nosia provides a self-hosted AI RAG + MCP platform for startup founders to manage and integrate their AI workflows in one place.

When to use it
  • •You need a centralized platform to manage multiple AI models and workflows
  • •Your startup requires a customizable and scalable AI solution
  • •You want to keep your AI data and workflows on-premise for security and compliance reasons
Ready-to-paste prompt
curl -X POST 'http://localhost:3000/api/v1/workflows' -H 'Content-Type: application/json' -d '{"name":"My Workflow","nodes":[{"type":"rag","prompt":"What is the meaning of life?"}]}'
Heads up: Make sure you have Ruby and the Bundler gem installed on your system before cloning and running nosia, as it is a Ruby-based application
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/nosia && curl -fsSL https://workflowstacks.com/api/skills/nosia/claude-skill -o ~/.claude/skills/nosia/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How nosia: AI RAG Platform works
Codeflow
Free to inspect

Nosia: AI RAG Platform is mostly documents (207 doc files, 261 small scripts) — something you read, not something you run. You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license.

Size
Mostly documents
207 documents · 261 small scripts · ~7 h to skim
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 45 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Ruby · Docker · needs API keys
Ruby 60%HTML 25%JavaScript 6%CSS 3%Shell 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    .env.example
    The API keys and settings you must provide
  4. 4
    app/javascript/controllers/index.js
    Inside app/ — the main logic begins here
What's in each folder
app/Core code — the actual logic299 files
lib/Core code — the actual logic30 files
bin/Command-line entry points14 files
docs/Documentation26 files
db/Folder72 files
config/Configuration31 files
tmp/Folder3 files
data/Data files1 files
READMEHas testsDocumentedCI checksDocker readyMIT licenseUpdated this month
Quick Actions
Details
Creator
dilolabs
Language
Ruby
Category
mcp-server
Published
6/10/2024

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 242,984
ECC: Optimize Performance
Get optimized performance with ECC, a research-first agent harness system for founders working with AI agents and developer tools like Claude Code and Codex
mcp-server★ 154,960
Dify: Streamline Workflow
Get a production-ready platform with Dify.
mcp-server★ 150,115
open-webui: Easy AI Interface
Get a user-friendly AI interface with open-webui, supporting Ollama and OpenAI API, for founders
mcp-server★ 113,199
Graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…
mcp-server★ 106,674
gemini-cli: AI in your terminal
Get AI power with gemini-cli,, 105k+ GitHub stars
mcp-server★ 82,036
LobeHub: 24/7 AI Team Management
Founders get organized AI operations with LobeHub. For startup founders managing AI teams.