Architecture
ChannelForge is a web application, a control plane and a GPU fleet. The web application is what people and programs talk to; the control plane does the work; the fleet renders. They meet in a PostgreSQL database and a Redis instance.
workspaces · teams · roles
API keys, signed deliveries
agents drive it as tools
pages, actions, OAuth connects, billing portal, admin console
Cloud SQL, Auth Proxy, nightly + 7-day PITR
queues, budgets, rate limits, progress
its own L4 boxes (1a, 1c), 2 slots each, sandboxed
Sonnet 5.5 · Opus 5.5 · Fable 5.1/5.2, via the gateway
tenant media (S3 API), private, per workspace
YouTube · Meta · LinkedIn · X TikTok · Threads · Bluesky…
The web application#
A Next.js 15 application in TypeScript (React 19 server components, server actions, Tailwind CSS) serves the marketing site, the documentation (82 pages), the signed-in product and the admin console (42 staff pages). Two instances run behind nginx, which retries a request on the other instance, so a deploy rolls one instance at a time; a release builds first and stops the control units around its migrations. Prisma maps the database's 313 tables.
The control plane#
| Service | Role |
|---|---|
| worker-cpu / worker-io / worker-film | job queues by resource: planning and copy; uploads and platform calls; film plans and audits |
| scheduler | slot decisions, autopilots, keep-ready buffers, generation per day |
| fleet | starts and stops GPU boxes, assigns jobs to slots, sets boxes up, installs code |
| sentinel | reaps dead jobs, prunes, alerts, enforces spending caps, runs privacy purges |
| gateway | a Node.js service, the only door to the models: it speaks the Anthropic Messages API, holds the one Bedrock credential, meters every call per workspace and job, and enforces budgets before a call |
| voice | the narration service (Chirp 3 HD) the GPU jobs call through a tunnel |
| mailer | transactional email through Amazon SES, deduplicated alerts |
| billing | Stripe events and PayPal resync, plan credits, invoices, disputes |
Every unit of work is a job with a kind, a resource, a state, attempts and an event log the customer can watch live. 2,735 jobs have run so far, of 47 kinds, from niche suggestions and channel drafts to episode generation, translations, films, insights and comment replies.
Data#
PostgreSQL 16 holds workspaces, users, teams, channels, episodes, posts, jobs, credits, plans, invoices, insights and the audit log — 313 tables. It runs on Google Cloud SQL, reached through the Cloud SQL Auth Proxy, with nightly backups and seven days of point-in-time recovery. Redis carries caches, budgets, rate limits and live progress. Media lives in a private Google Cloud Storage bucket, under one prefix per workspace.