Get private RAG and multi-model apps with Orbit, a self-hosted AI infrastructure for founders, with 276 GitHub stars.
276 stars47 forksPythonQuality 9/10Updated 6/5/2026100% free ยท open source
What it does
Provides a complete, self-hosted AI infrastructure that lets startups build private AI applications with full data control and flexible model integration.
When to use it
โขWhen you need a custom AI solution with sensitive data that can't be sent to external APIs
โขFor startups building enterprise AI tools requiring strict data privacy
โขWhen you want to easily switch between different AI models without vendor lock-in
Quick start
1Clone the GitHub repository
2Configure your desired AI models and data sources in the configuration files
3Set up your local or cloud deployment environment
4Launch the Orbit infrastructure and start building your AI application
Ready-to-paste prompt
python orbit.py --deploy-mode local --model mistral --datasource ./company_documents
Saves to your device
Topics
ai-assistant
ai-gateway
ai-safety
anthropic
chatbot
developer-tools
elasticsearch
llm
mongodb
natural-language-to-sql
ollama-client
openai
python
rag
retrieval-augmented-generation
self-hosted
speech-to-text
text-to-speech
vector-database
What's inside โ free to inspect
No purchase needed
Read the entire source before you build โ unlike paid marketplaces that hide it behind a buy button.