hwdsl2/self-hosted-ai-stack

by hwdsl2 · Self-Hosted Platforms · updated today

Deploy a complete self-hosted AI stack with Docker Compose: Ollama, LiteLLM, AnythingLLM, Whisper, WhisperLive, Kokoro, Embeddings, Docling and MCP Gateway. Local-first, private by default, with lightweight stacks, optional HTTPS and NVIDIA CUDA acceleration. Multi-arch: amd64, arm64.

More in Self-Hosted Platforms

oriveo

oriveo

32

Self-Hosted Platforms

Open-source, bring-your-own-key (BYOK) multi-model AI chat client for iOS, Android and the

TokenHub

astaxie

41

Self-Hosted Platforms

TokenHub gives enterprises a private gateway to unify AI model access and governance, maki

AIHelms

beizhu-1209

53

Self-Hosted Platforms

企业级 AI 资源纳管平台，提供统一 AI网关、Token调度能力，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill

gemini-web2api-go

zexadev

81

Self-Hosted Platforms

Gemini web → OpenAI-compatible API, self-hosted, no API key. Reverse-proxies gemini.google