{"name":"nosia: Self-Host AI RAG and MCP on Your Data","description":"Nosia is a self-hosted AI platform built with Ruby on Rails and PostgreSQL with pgvector, combining document-based RAG with MCP tool connections. It offers an OpenAI-compatible API and Docker Compose installation for macOS, Linux, and Windows.","github":"https://github.com/dilolabs/nosia","url":"https://osrepos.com/repo/dilolabs-nosia","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/dilolabs-nosia","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/dilolabs-nosia.md","json":"https://osrepos.com/repo/dilolabs-nosia.json","topics":["ruby","self-hosted","ai","rag","mcp","openai-compatible-api","document-search"],"keywords":["ruby","self-hosted","ai","rag","mcp","openai-compatible-api","document-search"],"stars":null,"summary":"Nosia is a self-hosted AI platform built with Ruby on Rails and PostgreSQL with pgvector, combining document-based RAG with MCP tool connections. It offers an OpenAI-compatible API and Docker Compose installation for macOS, Linux, and Windows.","content":"## Overview\n\nNosia is a self-hosted AI RAG and MCP platform built with Ruby on Rails and PostgreSQL with pgvector. It lets teams query their own documents and connect AI models to external tools and data sources, while keeping the application and data on infrastructure they control. OpenAI-compatible endpoints let existing clients connect to Nosia.\n\nThe project is aimed at people who want a packaged platform rather than assembling separate document search, chat, and MCP components. Its Docker Compose setup targets macOS, Debian, Ubuntu, and Windows, and the README describes using Docker Hub AI models by default, with configuration for other compatible model services.\n\n## Key Features\n\n- Index PDFs, text files, websites, and question-and-answer pairs for semantic search.\n- Add retrieved document context to chat completions through configurable RAG.\n- Connect MCP servers over stdio, SSE, or HTTP so chats can use external tools and resources.\n- Expose an OpenAI-compatible API with streaming responses.\n- Provide account-based data isolation and a web interface for documents, chats, and integrations.\n- Run the application and supporting services with Docker Compose.\n- Extend chat behavior with custom LLM-driven and Ruby-based skills.\n\n## Use Cases\n\n- A small team can ask questions over internal documents without sending those documents to a hosted knowledge platform.\n- Developers can connect existing OpenAI-compatible clients to a self-hosted endpoint for document-grounded chat.\n- Teams can give an assistant access to selected calendars, file stores, or messaging tools through MCP servers.\n- Administrators can deploy a shared, account-isolated AI workspace when they are prepared to operate its Docker-based services.\n\n## Our Take\nNosia is an actively maintained, broad self-hosted AI platform with a recent release cadence, but adopting it means operating a multi-service Docker deployment and checking how the current issue backlog is handled.\n\n**Good fit if:**\n- You want document RAG and MCP integrations in one self-hosted Ruby on Rails application.\n- Your users need OpenAI-compatible API access as well as a web interface.\n- You can run Docker Compose and configure the model and embedding services that suit your environment.\n\n**Look elsewhere if:**\n- You need a standalone library or a lightweight service without a web app and supporting containers.\n- You require a hosted service or do not want responsibility for deployment, model configuration, and data backups.\n- Your use case does not need both document retrieval and MCP tool integrations.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **Active**: regular commits and releases |\n| Last commit | 2026-10-15 (today) |\n| Commits, last 90 days | 33 |\n| Releases, last 12 months | 20 (latest v0.5.3, 2026-07-12) |\n| Contributors | 6 (top contributor: 72% of commits) |\n| Issues closed, last 90 days | 0 |\n| Pull requests merged, last 90 days | 6 (typically merged in 0 days) |\n| Project age | 2 years |\n\nChecked on 2026-10-15 with the GitHub API.\n\n## Project Facts\n\n- Language: Ruby\n- License: MIT\n- Stars: 214\n- Forks: 20\n- Topics: ai, all-in-one, docker, embedding, llm, mcp, rag, ruby\n- Website: https://hub.docker.com/r/dilolabs/nosia\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Ruby (from Gemfile)\n- A Dockerfile, so it can run in a container; a Compose file sets up the related services\n- A test suite and automated checks on GitHub Actions\n\n## Getting Started\n\nOn macOS or Linux, the README provides a one-command installer:\n\n```sh\ncurl -fsSL https://get.nosia.ai | sh\n```\n\nThen start the services with `docker compose up -d` and visit `https://nosia.localhost`. The README and deployment guide cover configuration, production TLS, and upgrades: [README](https://github.com/dilolabs/nosia) and [deployment guide](https://github.com/dilolabs/nosia/blob/main/docs/DEPLOYMENT.md).\n\n## License in Plain Words\n\n**MIT** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the copyright and license notice\n- Share your changes: no\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [MaxKB](https://osrepos.com/repo/1panel-dev-maxkb): MaxKB centers on building knowledge-based agents and workflows, while Nosia combines document RAG and MCP connections with an OpenAI-compatible API.\n- [rag-agent-platform](https://osrepos.com/repo/nedonion-rag-agent-platform): rag-agent-platform uses Java and Next.js for configurable retrieval, agent, and MCP workflows; Nosia is a Rails and PostgreSQL platform with an OpenAI-compatible API.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **nosia** | Ruby | MIT | 214 | Active |\n| [MaxKB](https://osrepos.com/repo/1panel-dev-maxkb) | Python | GPL-3.0 | 22.9k | Active |\n| [rag-agent-platform](https://osrepos.com/repo/nedonion-rag-agent-platform) | Java | MIT | 89 | Active |\n\n## Considerations\n\n- This is an application stack, not a single executable: Docker Compose runs the web application alongside services including PostgreSQL, model, embedding, and background-job components.\n- The README's default setup uses Docker Hub AI models. Model choice, embedding dimensions, and compatible AI service configuration need to match the deployment; changing embedding dimensions can require rebuilding existing embeddings.\n- The default local endpoint uses a self-signed certificate. Production deployments need proper SSL configuration, and the README notes that Windows users may need to add `nosia.localhost` to their hosts file.\n- The project is active, with regular commits and releases, and contributions from multiple people. However, the measured record shows no issues closed in the recent 90-day period, so teams should evaluate their support expectations and review open issues.\n- The MIT license permits broad use, subject to its license terms and notices.","metrics":{"detailViews":2,"githubClicks":1},"dates":{"published":null,"modified":"2026-10-15T20:44:26.000Z"}}