Skip to main content
Sign In

The orchestrator for
agentic workloads.

A fast, high-density and scalable orchestrator for every workload an agent needs.Open-source and self-hostable.

Start Building
Give this to your coding agent
Introducing OpenTelemetry for Rivet Actors and Workflows

Whatever the workload, there’s an Actor for it.

Actors

Give every agent a durable process to live in

Workflows

Multi-step operations that replay instead of starting over

Sandboxes

A filesystem, shell, and network for code you did not write

Preview
Dynamic Apps

A backend per user, deployed the moment it is generated

Explore more Actors
  • Durable Streams
  • Vercel Eve
  • Vercel Workflow SDK
  • Flue
Build your own Actor

Built for everything agents need.

Run 2,829× more workloads per server.

An Actor lives inside a worker process you already run, not in its own container or VM. A server that held hundreds of pods holds hundreds of thousands of Actors.

72.4 KBper running ActorRSS increase per running Actor. Measured on FoundationDB with the Rust rivetkit SDK.

Rivet Actors
0 × 72.4 KB

Kubernetes pods
0 × 200 MB

Start in milliseconds, not minutes.

A cold start includes scheduling the Actor, loading its state, and serving the first request. No image pull, no container boot.

12.3 mscold startRound trip of an HTTP request waking an Actor from hibernation: 12.3 ms p50, 27.7 ms p99. Measured on FoundationDB with the Rust rivetkit SDK. Uses an experimental Rivet feature that will be enabled by default in an upcoming update.

Rivet Actor
12.3 ms

Kubernetes pod
~6 s

Built for scale.

Actors are scheduled independently, so adding capacity means adding machines. The same control plane runs a thousand Actors or a billion.

Billionsof Actors
Billions of Actors on one control plane.

Hibernates when idle, wakes on demand.

An idle Actor writes its state and unloads. The next request brings it back in 12.3 ms with nothing lost.

0 MBwhile hibernating

Durable state for every workload.

Every Actor gets a SQLite database and a POSIX filesystem, tiered to S3. Idle Actors cost nothing, so millions can sit parked with their state intact.

  • SQLite
  • POSIX filesystem
  • S3 tiered storage
A plane of thirty-six small databases, one per Actor, with writes landing on them continuously.

Run code agents generate at runtime.

An agent writes a script mid-task to get something done, or your product generates a whole backend for a user who described what they wanted. Either way the code is new, untrusted, and needs to run now — so each piece gets an Actor of its own, with its own database and filesystem and no reach into anyone else's. Nothing to provision first, and nothing running once it goes idle.

Three streams of AI-generated code flow into a converter, and a stream of Actors flows out the other side.

Works with the tools you already use.

Typed SDKs for your backend and React hooks for your frontend.

  • TypeScript
  • Node.js
  • Rust
  • React
  • Effect

Other powerful features of the Rivet Orchestrator.

Routing, scheduling, types, and telemetry, built in.

Fault tolerance by designA worker going down reschedules its Actors elsewhere with their state intact. No replay harness or checkpointing of your own.Multi-regionPlace Actors near the users and data they serve, and route requests to wherever each one currently lives.HTTP & WebSocket networkingAddress an Actor directly over HTTP or hold a live WebSocket to it. No queue or broker in between.End-to-end type safetyActor definitions generate their own client types, so a signature change breaks the build rather than production.React SDKFirst-party hooks that subscribe a component to an Actor's state and keep it live as the Actor updates.OpenTelemetry & observabilityTraces, metrics, and structured logs emitted in OTel format, into the collector you already run.Single Rust binaryThe control plane ships as one static binary with no external dependencies to stand up first.Cron & schedulingWake an Actor on a schedule or at a timestamp it sets for itself, without a separate scheduler.Sleeps when idleIdle Actors release their resources and wake with durable state intact when the next request arrives.Actor-to-actor callsActors address each other by key and call across the cluster as if the other one were local.No Kubernetes operatorOne control plane behind a load balancer, speaking plain HTTP inside your VPC. No CRDs, no operator, no service mesh to keep alive.Open sourceApache 2.0, self-hostable in full. The managed service runs the same control plane you can run yourself.

Run your agent infrastructure where your data already lives.

  • Single Rust binary

    One process to install, monitor, and upgrade, on Kubernetes with the Enterprise Helm chart or as a systemd unit.

  • Managed in your VPC

    With BYOC, Rivet deploys and maintains the control plane inside your cloud over an outbound connection.

  • Storage you control

    Use Postgres or FoundationDB for persistence and tiered storage to S3.

  • Local dev matches production

    Use the same binary, APIs, and control-plane behavior from laptop to production.

Talk to an engineerExplore Enterprise

Supported clouds

  • Docker Compose
  • Kubernetes
  • Virtual Machine
  • AWS ECS
  • Railway
  • Render
  • Custom Platform

Start local. Deploy when ready.

Local & Self-Host

Install Actors and run it locally while you build. When you ship, run the same open-source control plane as a Rust binary or container on your own infrastructure.

Open the quickstartRead self-hosting docs

Rivet Cloud

Deploy Actors on Rivet Cloud with managed infrastructure and persisted Actor data.

Open the dashboard

BYOC

Run the control plane inside your own VPC, fully managed by Rivet. Your data never leaves your cloud and there is no inbound management connection.

Read the BYOC docs

Frequently asked questions

Orchestration for agentic workloads.

Run agents, workflows, and sandboxes as durable Actors — on your infrastructure or ours.

Start Building Talk to an Engineer