墨台 VibeHolding：AI 时代全链路基建选型知识库（A–V 图廓 · 关系边 · 方案）+ 桌面/Web 客户端。本地优先，内容可 PR。
Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP tools. Powered by Ollama, LiteLLM, AnythingLLM and more. Local-first with auto-configured authentication, lightweight stacks, optional HTTPS and NVIDIA GPU support. MIT licensed. Multi-arch: amd64, arm64.
🚀 AI LaunchKit - Complete self-hosted AI development toolkit with 50+ pre-configured tools including n8n, bolt.diy, ComfyUI, and more. One-command installation.
Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance evidence (Strix Halo, DGX Spark, llama.cpp, vLLM): https://agmind.ai
Curated AI tools, Claude skills, MCP servers & growth playbooks for solopreneurs, indie hackers and solo founders — the one-person-company AI stack you feed to Claude Code.
Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)
The Opinionated AI Stack Guide — 66 tools, 13 categories, evidence-first
Research and shared data contracts for Pick Your AI: component catalogs, compatibility rules, pricing, and evidence for AI stacks.
Turn any GPU server into a production-ready private AI appliance. One-command deployment for LLM inference, RAG, observability, and workflow automation.
Pick Your AI: a PCPartPicker-inspired builder for complete AI stacks. Explore components, compatibility, and costs in a preview using synthetic data.
Codex skill for generating enterprise Word documents from a sanitized DOCX template
Organization profile, contribution guidance, and shared community health files for Pick Your AI, a PCPartPicker-inspired AI stack builder.
Self-hosted local-first AI research stack with Ollama, n8n, USMC & GARDENER memory, task-master, KnowledgeDigest, and Docker Compose
Easy-to-deploy OpenLiteSpeed Docker reverse proxy for multiple applications and services, including HTTPS/SSL setup, ACME, HTTP/3, WebSocket and security support.
The **Podman AI Stack** is a secure, configurable, and systemd-native orchestration stack for deploying containerized AI environments (Open WebUI and Ollama). It leverages **Podman Quadlets** to provide a seamless integration with systemd, supporting both rootless and rootfull deployments on Fedora and other RPM-based distributions.
Personal backup for my agentic coding setup.
AI thematic investing across the five-layer AI stack: an objective, layer-structured framework for classifying AI companies, mapping value migration, measuring circular financing, and factor-based portfolio construction — with a falsifiable backtest and AI-index/ETF benchmarks. Educational research, not investment advice.
Complete self-hosted AI server stack on the Nvidia DGX Spark (arm64)
The report card for Ai stacks.
To associate your repository with the ai-stack topic, visit your repo's landing page and select "manage topics."