rivet-dev

Deploy, configure, and integrate Sandbox Agent - a universal API for orchestrating AI coding agents (Claude Code, Codex, OpenCode, Amp) in sandboxed environments. Use when setting up sandbox-agent server locally or in cloud sandboxes (E2B, Daytona, Docker), creating and managing agent sessions via SDK or API, streaming agent events and handling human-in-the-loop interactions, building chat UIs for coding agents, or understanding the universal schema for agent responses.

RivetKit backend and Rivet Actor runtime guidance. Use for building, modifying, debugging, or testing Rivet Actors, registries, serverless/runner modes, deployment, or actor-based workflows.

RivetKit JavaScript client guidance. Use for browser, Node.js, or Bun clients that connect to Rivet Actors with rivetkit/client, create clients, call actions, or manage connections.

RivetKit React client guidance. Use for React apps that connect to Rivet Actors with @rivetkit/react, create hooks with createRivetKit, or manage realtime state with useActor.

RivetKit SwiftUI client guidance. Use for SwiftUI apps that connect to Rivet Actors with RivetKitSwiftUI, @Actor, rivetKit view modifiers, and SwiftUI bindings.

RivetKit Swift client guidance. Use for Swift clients that connect to Rivet Actors with RivetKitClient, create actor handles, call actions, or manage connections.

Pragmatic patterns for building multiplayer games: matchmaking, tick loops, realtime state, interest management, and validation.

Actors: The primitive for agent orchestration.

agentOS: A computer for every agent.

Workflows: Durable, replayable multi-step operations.

Dynamic Apps: Deploy an AI-generated backend for every user.

Patterns for durable one-shot, calendar, and fixed-interval work on Rivet Actors.

Build an AI agent backend with persistent memory: one Rivet Actor per conversation, queued message handling, and streaming LLM responses as realtime events.

Build a realtime chat room backend with Rivet Actors: one actor per room, SQLite-backed message history, and WebSocket broadcast to every connected client.

Give every AI agent its own computer: a persistent workspace with a filesystem, processes, shells, networking, and agent sessions on a lightweight in-process OS.

Multi-tenant data isolation with one Rivet Actor per tenant: the actor key is the tenant id, so each tenant gets its own isolated dataset and migrations.

Build a collaborative text editor backend with Yjs CRDTs and Rivet Actors: per-document actors relay sync and awareness updates and persist snapshots.

Live cursors and multiplayer presence with Rivet Actors: per-connection cursor state, realtime updates over events or raw WebSockets, and throttling.

Run Rivet entirely inside your own perimeter: single-binary or Docker Compose install, file system storage with no database infrastructure, and no outbound telemetry by default.

Secure Exec: Secure Node.js execution without a sandbox.

RivetKit Rust client guidance. Use for Rust clients and backends that connect to Rivet Actors with rivetkit::client, create typed actor handles, call actions, or manage connections.