Self-host the AI stack
you actually control.
Find self-hosted alternatives to popular AI tools. Each tool comes with verified RAM, CPU and GPU requirements, plus the exact VPS size you need to run it.
[ FEATURED ]
Where we'd start.
Well documented and permissively licensed, with specs verified on a real deployment.
ComfyUI
Node-based UI for Stable Diffusion, Flux and beyond.
Dify
Self-hosted LLM app platform with datasets, agents, observability.
n8n
Workflow automation with first-class AI nodes.
Ollama
Run open-weight LLMs locally with one command.
Open WebUI
A full-featured self-hosted ChatGPT alternative.
Perplexica
Self-hosted Perplexity alternative: AI search with citations.
vLLM
High-throughput LLM serving for production GPU workloads.
[ CATEGORIES ]
By stack layer.
Every tool grouped by what it does in your stack, from the runtime to the UI on top.
[ INDEX ]
All entries.
AnythingLLM
Chat with your documents: workspaces, embeddings, agents in one container.
AUTOMATIC1111 WebUI
The classic Stable Diffusion web UI.
Chroma
A lightweight vector database for prototyping.
ComfyUI
Node-based UI for Stable Diffusion, Flux and beyond.
Continue
Open-source Copilot for VS Code and JetBrains; bring your own model.
Dify
Self-hosted LLM app platform with datasets, agents, observability.
Flowise
Drag-and-drop builder for LangChain flows.
Hollama
Minimal, fast Ollama and OpenAI client. No backend.
InvokeAI
Polished, production-leaning Stable Diffusion studio.
Khoj
Personal AI that searches your notes, files and the web.
Langflow
Visual flow builder for LangChain, backed by IBM.
LibreChat
Multi-provider chat UI with agent and tool support.
llama.cpp
The C/C++ LLM inference engine that runs everywhere.
LocalAI
Drop-in OpenAI-compatible API for local models.
n8n
Workflow automation with first-class AI nodes.
Ollama
Run open-weight LLMs locally with one command.
Onyx
Self-hosted enterprise search and chat over your team's data.
Open WebUI
A full-featured self-hosted ChatGPT alternative.
Perplexica
Self-hosted Perplexity alternative: AI search with citations.
Piper
Fast, lightweight neural text-to-speech.
Qdrant
Fast Rust-based vector database with great DX.
Tabby
Self-hosted GitHub Copilot, full backend included.
vLLM
High-throughput LLM serving for production GPU workloads.
Weaviate
Vector DB with built-in hybrid search and modular embeddings.
whisper.cpp
OpenAI Whisper in C/C++, CPU-friendly transcription.