June 12, 2026·5 min read
Building Forge: Postgres-Orchestrated LLM Batch and Realtime Jobs Without a Queue
Forge runs LLM batch and realtime jobs across OpenAI and Anthropic with two Node daemons that share nothing but a Postgres database. No queue, no IPC, no shared worker process — the database does the coordinating. Here is how that architecture works and what I learned building it.
aillminfrastructurepostgresarchitecture