Launch HN: Rivet (YC W23) – Scale and Orchestrate Agents on S3

Practical AI: Tools, Models & Frameworksframework

What changed

4.99 ms p99 cold starts, 72 KB RAM per Actor, scales to billions Quickstart • Documentation • Blog • Discord • X Rivet Actors are long-lived processes with in-memory state, a SQLite database, WebSockets, and scheduling. You can create one for each agent, user, session, or tenant. - 72 KB per Actor: Actors share a node process instead of each booting a sandbox, so one server holds hundreds of thousands.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

  • Show HN: Whiteboard (YC W26) – An open-source IDE for thoughtful software design
  • Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents
  • OpenSpec – A lightweight and configurable AI spec framework

Sources