Tag: ai

Skeleton Key MCP swaps four narrow homelab tokens for one Vaultwarden vault and one OAuth consent flow. Here is what that buys you, and what it risks.

I ran TypeSafe's Jev model against 840 blog posts to fix tag drift. Real cost numbers, benchmarked accuracy, and the failure mode that almost cost pageviews.

Two Proxmox MCP servers can query your cluster over chat, but the real safety boundary is a scoped PVEAuditor API token, not a config permission flag.

Home Assistant ships two MCP integrations, not one. One turns your house into a server for Claude and ChatGPT. The other is narrower than its name suggests.

Komodo's community MCP server beats mounting the Docker socket or handing an AI agent SSH: scoped auth, per-tool RBAC, and confirmation before deletes.

Nano Banana's blurry images come from two causes: permanent generational loss from iterative editing, and a June 2026 outage Google fixed within 15 hours.

Coding agents write flawless code and leave hero.png blank. Compare self-hosted GPU image generation against subpixel, a ChatGPT-subscription CLI tool.

Aider offers interactive CLI-based pair programming with git awareness. Continue provides IDE-integrated AI assistance. Learn when to use each.

An AI coding agent rebuilding the same tag all day fills a disk fast. The mechanism, the truth about volume pruning, and a systemd timer that fixes it.

Anubis puts a proof-of-work gate in front of your site. Real policy file config, weights and thresholds, Caddy wiring, and the false positives you hit.

What is an AI harness? A plain-language answer, plus 21 of them grouped by job: Claude Code, Codex CLI, Kilo Code, Goose, OpenHands and DeepSeek Harness.

Run several Claude Code accounts on one Linux machine. CLAUDE_CONFIG_DIR plus symlinks share your skills, hooks and history while each login stays isolated.