Rivet
The primitive for AI agents and the systems they operate.
Rivet provides infrastructure for AI agents and stateful workloads, offering actors that hold state, run long-lived workflows, and scale globally. It includes agentOS, a lightweight open-source operating system for agents built on WASM and V8, with built-in observability tools for debugging and monitoring. Developers can run Rivet locally via the RivetKit library, self-host on their own infrastructure, or use Rivet Cloud for a fully managed option.
Developers install RivetKit as a library and connect it to Rivet Cloud or a self-hosted binary to run stateful actors, durable workflows, and agentOS sandboxes with built-in observability.
Developers and teams building AI agents and stateful, long-running backend workloads
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.