Self-Hosted Apps

3apps · local AI compatibility & hardware requirements

Self-hosted AI apps run on your own infrastructure — your hardware, your data, your control. These range from simple single-user desktop apps to multi-user Docker deployments with admin panels and SSO. Running self-hosted means you are not sending data to third-party servers, which is important for privacy-sensitive use cases.

AnythingLLM
All-in-one local AI workspace with best-in-class RAG. Upload documents, chat with your files, build no-code AI agents, and connect 30+ LLM providers.
Runs locally · OpenRouter
LibreChat
Enterprise self-hosted ChatGPT clone with 30+ AI providers. Multi-user admin panel, OAuth2 SSO, artifacts, code interpreter, and MCP support.
· OpenRouter
Open WebUI
Self-hosted ChatGPT-like web UI for LLMs. Native Ollama integration, RAG document Q&A, multi-user support, and OpenRouter compatibility.
Runs locally · OpenRouter

Want to check if your GPU can run the models these apps need? Use the homepage calculator to see which models fit your hardware with estimated tokens per second.