Self-Hosted

Developer Tools 4 min How to Self-Host Nextcloud with Docker The first decision is not a setting: there are two official deployment routes and they are not variations on e... KE Kenji Tanaka 31 Aug Developer Tools 5 min How to Back Up a Docker Stack Every self-hosting guide ends by telling you to back it up and none of them say how. Three things live in diff... KE Kenji Tanaka 31 Aug AI & ML 7 min How to Measure Whether Your RAG Is Retrieving the Right Documents Twenty questions with known answers, run over 205 real documents. Prefixing titles to chunks raised hit@1 from... KE Kenji Tanaka 21 Aug AI & ML 5 min How to Give an Agent Search Over Your Own Documents Seventy-eight lines with no dependencies join a local embedding model, a vector store and MCP. The interesting... KE Kenji Tanaka 21 Aug AI & ML 6 min How to Generate Embeddings Locally A 46 MB model, running on your laptop, turns text into positions in space. The demonstration: a query whose on... KE Kenji Tanaka 21 Aug AI & ML 6 min How to Self-Host Qdrant in Docker Every retrieval tutorial says "point it at your vector database" and none of them tells you how to run one. On... KE Kenji Tanaka 21 Aug Cloud & Infra 5 min What One Server Actually Runs This publication — the live site, a full staging copy, an error tracker and its own CI runner — is four cores... KE Kenji Tanaka 21 Aug Developer Tools 7 min What We Actually Run, and What It Would Cost Managed Our whole production stack holds 1.48 GiB — 70% of it MySQL, and just 107.8 MiB serving every page. The surpri... MA Maya Lin 18 Aug AI & ML 23 min Serve an LLM with vLLM on CPU in Docker: Learn the Production Engine Without a GPU (2026) We ran vLLM v0.25.1's official CPU image in Docker on Apple Silicon, dodged a 10 GB CUDA decoy, survived three... KE Kenji Tanaka 22 Jul AI & ML 16 min Run ComfyUI on CPU in Docker: Node-Graph Image Generation Without a GPU (2026) We pinned ComfyUI v0.28.0 in a python:3.13-slim container, hit a torchaudio ABI trap and an 8 GB OOM kill, and... KE Kenji Tanaka 22 Jul AI & ML 14 min Self-Host LiteLLM with Docker: One OpenAI-Compatible Endpoint for Every Model (2026) We ran LiteLLM v1.93.0 against a local Ollama model in Docker: pinned tags, a 4-line config, token metering, a... KE Kenji Tanaka 22 Jul AI & ML 15 min How to Transcribe Speech Offline with whisper.cpp in Docker (2026) We ran whisper.cpp v1.9.1 in Docker: an amd64-only tag trap, a SIGILL crash, a gcc fp16 build fix — then 7.3 s... KE Kenji Tanaka 22 Jul AI & ML 17 min How to Run Aider With a Local Ollama Model in Docker (2026) We ran aider v0.86.2 in Docker against a 986 MB local Qwen model. Same prompt twice: one hallucinated diff, on... KE Kenji Tanaka 21 Jul AI & ML 17 min How to Self-Host AnythingLLM with Docker and Ollama (2026) We self-hosted AnythingLLM 1.15.0 with Docker and Ollama, embedded a document over the API, and got cited RAG... KE Kenji Tanaka 21 Jul AI & ML 18 min How to Self-Host the AutoGPT Platform with Docker (2026) We self-hosted the AutoGPT Platform v0.6.68 with Docker on a busy dev Mac: 17 containers, two port collisions,... KE Kenji Tanaka 21 Jul AI & ML 16 min Self-Host Langflow with Docker: The Visual Agent Builder, Locked Down (2026) We ran Langflow 1.10.2 in a single Docker container, hit its fail-closed auth gate, fixed it with explicit sup... KE Kenji Tanaka 21 Jul Developer Tools 16 min Self-Host Firecrawl with Docker: Scrape the Web into LLM-Ready Markdown (2026) We cloned Firecrawl v2.11.0, built its seven-service Docker stack, and scraped our own homepage into clean mar... KE Kenji Tanaka 21 Jul AI & ML 16 min Self-Host Dify with Docker Compose: 15 Containers to Your Own LLM App Studio (2026) We deployed Dify 1.16.0 on Docker Desktop, hit a real port clash, wired DeepSeek, and built a working chatflow... KE Kenji Tanaka 21 Jul AI & ML 15 min Run a Private ChatGPT in Docker: Open WebUI + Ollama (2026) We wired Open WebUI v0.10.2 to Ollama 0.32.1 in two pinned Docker containers, hit one tools-support snag, and... KE Kenji Tanaka 21 Jul Developer Tools 14 min Self-Host n8n with Docker: From Zero to Your First Webhook (2026) One container, one volume, one real webhook: we self-hosted n8n 2.30.8 with Docker on macOS and captured every... KE Kenji Tanaka 21 Jul AI & ML 18 min How to Self-Host OpenClaw in Docker (2026): Run the 383k-Star AI Agent in a Box We ran OpenClaw 2026.7.1 in Docker on an Apple Silicon Mac: one setup script, a DeepSeek model, two real confi... KE Kenji Tanaka 20 Jul AI & ML 9 min The Best Open-Source LLMs You Can Actually Self-Host (2026) Qwen, Llama, DeepSeek, Mistral, Phi and Gemma compared for self-hosting in 2026 — precise licenses, real hardw... KE Kenji Tanaka 14 Jul