A faster, lighter, cheaper alternative to sandboxes.
Run any coding agent inside an isolated Linux VM, with agent orchestration built in.
Pi
Claude Code
Codex
OpenCodeA new architecture.
Built from the ground up for lightweight agents. agentOS provides the flexibility of Linux with lower overhead than sandboxes.
WebAssembly + V8 Isolates
High-performance virtualization without specialized infrastructure. The same battle-hardened isolation technology that powers Google Chrome.
Battle-tested technology
You're probably using this technology right now to view this page. Bring the same power to your agents. No VMs, no containers, no overhead.
Performance benchmarks
agentOS vs. traditional sandboxes.
Workload: Pi coding agent session with MCP servers and mounted file systems
Why the gap: agentOS runs agents in-process — V8 isolates and Wasm inside your host. No VM to boot, no network hop, no disk image. Sandboxes must boot an entire environment, allocate memory, and establish a network connection before code can run.
Sandbox baseline: E2B, the fastest mainstream sandbox provider as of March 30, 2026.
agentOS: Median of 10,000 runs (100 iterations x 100 samples) on Intel i7-12700KF.6.1 ms
Why the gap: In-process isolates share the host's memory. Each additional execution only adds its own heap and stack. Sandboxes allocate a dedicated environment with a minimum memory reservation, even if the code inside uses far less.
Sandbox baseline: Daytona, the cheapest mainstream sandbox provider as of March 30, 2026. Default sandbox: 1 vCPU + 1 GiB RAM.
agentOS: ~131 MB for a full Pi coding agent session with MCP servers and file system mounts.~131 MB
Sandboxes reserve idle RAM per agent.
server price per second / concurrent executions per serverWhy it's cheaper: Each execution uses ~131 MB instead of a ~1024 MB sandbox minimum. And you run on your own hardware, which is significantly cheaper than per-second sandbox billing.
Sandbox baseline: Daytona, the cheapest mainstream sandbox provider as of March 30, 2026. Default sandbox: 1 vCPU + 1 GiB RAM at $0.0504/vCPU-h + $0.0162/GiB-h.
agentOS: ~131 MB baseline per execution, assuming 70% utilization (industry-standard HPA scaling threshold). Select a hardware tier above to compare.$0.000000066/s
Assumes one agent per sandbox, needed for isolation.
Measured on Intel i7-12700KF. Cold start baseline: E2B, the fastest mainstream sandbox provider as of March 30, 2026. Cost baseline: Daytona, the cheapest mainstream sandbox provider as of March 30, 2026 (1 vCPU + 1 GiB default). Cost assumes 70% utilization on self-hosted hardware vs. per-second sandbox billing. Benchmark document
An operating system for your agents.
A full file system, networking, scheduling, and resource control — everything the agent needs to do real work, built into one npm package.
Any agent harness
Claude Code, Codex, OpenCode, and Pi all run behind one unified API. Swap or add agents without touching your infrastructure.
File system
Mount S3, GitHub, or a database as the agent’s file system. The host scopes access, so there are no per-agent credentials.
Preview deployments
Every app the agent runs gets its own unique preview URL, served straight from the VM.
Sandbox mounting
agentOS handles most workloads — dev servers, CLIs, builds — in-process, and mounts a full sandbox when a job needs a real kernel, native binaries, or a GPU.
Resource limits
Per-agent CPU, memory, and network limits. One isolate can’t crash or starve the rest.
Orchestrate fleets of agents in a few lines of code.
import { createClient } from "@rivet-dev/agentos/client";
import type { registry } from "./server";
const client = createClient<typeof registry>("http://localhost:6420");
const agent = client.vm.getOrCreate("my-agent").connect();
// Stream events (tool calls, text output, etc.)
agent.on("sessionEvent", (data) => console.log(data.event));
// Create a session and send a prompt
const session = await agent.createSession("pi", { env: { ANTHROPIC_API_KEY: process.env.ANTHROPIC_API_KEY! } });
await agent.sendPrompt(session.sessionId, "Write a Python script that calculates pi");Durable sessions
Every run is a managed session with its own state, history, and lifecycle. Pause, resume, and replay.
Workflows
Chain durable, multi-step workflows that survive restarts and pick up exactly where they left off.
Agent-to-agent
Let agents delegate to other agents through host-brokered calls, under the same limits and permissions.
Tools, MCP & skills
Write tools as JavaScript functions on the host, connect any MCP server, and add skills the agent can call.
Approvals & queue-in-loop
Gate sensitive actions behind human approval and queue work for review in the loop.
Observability
Stream every event, tool call, and state change for full visibility into what your agents are doing.
agentOS Registry
A marketplace for agent capabilities. Browse and install pre-built tools, integrations, file systems, databases, and sandboxes — one command away.
Start local. Scale to millions.
A library in development, a platform in production. agentOS runs in your process locally and deploys wherever you already ship — the same SDK, no rewrites.
Local Development as a Library
Install a package and run locally. No servers, no infrastructure — VMs and agents run in your process during development.
Get Started
Rivet Cloud
Fully managed agentOS on a global edge network. Bring your own cloud or run on Rivet Compute. Zero-ops, scales to millions of agents.
Sign UpSelf-Host
Run the open-source Rivet platform on your own infrastructure — Kubernetes, Hetzner, VMs, and more.
Self-Hosting Docs