James Washington
writing about archive utils free game ideas replays
API

LiteLLM-as-container job engine behind a DO binding

The backend that runs paid AI document jobs for a small SaaS.

built Apr 2024 updated Oct 2026 Cloudflare and the edge

how it works

Config-only LiteLLM in a Cloudflare Container reached over an internal Durable Object binding: no public hostname, no tunnel, no Access policy needed.

API: A service other programs can call.

The code for this one lives in a private repo. This page explains the idea so you can build your own.

cloudflare-containerslitellmprivate-networking

related

  • Marked-up LLM gateway with per-client virtual keys and Stripe invoicing API A private AI service that lets a consultancy give each client their own AI key and bill them monthly for exactly what they used.
  • OrbStack container gotchas on a Mac server Technique Hard-won traps running ~30 containers on a Mac.
  • imagegen skill (gateway + fallback + text overlay) AI skill Generates cover art and illustrations, then adds clean title text on top.
  • Mac Mini homelab Document A home server that runs the household's smart-home, AI chat, monitoring and backup services.
  • Omni-token + pinned account_id Technique Give AI agents one all-powerful cloud key, but make every project refuse to deploy anywhere except its own account.
← everything I've built
© 2026 James Washington
github twitter rss