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 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.
🚀 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.
The Opinionated AI Stack Guide — 66 tools, 13 categories, evidence-first
Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)
Turn any GPU server into a production-ready private AI appliance. One-command deployment for LLM inference, RAG, observability, and workflow automation.
Codex skill for generating enterprise Word documents from a sanitized DOCX template
Self-hosted local-first AI research stack with Ollama, n8n, USMC & GARDENER memory, task-master, KnowledgeDigest, and Docker Compose
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.
The report card for Ai stacks.
Patched Qualcomm AI Stack SDK fixing critical memory corruption and shape inference bugs in model converter tools (QNN/SNPE).
A fully local, Docker-based AI stack mimicking Anthropic Claude using open-source LLMs (Ollama + LiteLLM + Open WebUI). No cloud dependency required.
Local AI operator stack for Windows 11 and WSL2 with LiteLLM, Ollama, Open WebUI, and governance tooling.
Ready-to-use AI tool stacks for Marketers, Developers, Designers, Content Creators, Founders and more — curated by mrreviewai.com
Vollständig lokaler LLM‑Stack unter Ubuntu: LM Studio + Dolphin 3 + AnythingLLM mit Offline‑RAG und Dokumentanalyse.
To associate your repository with the ai-stack topic, visit your repo's landing page and select "manage topics."