Rivet.dev: An open-source alternative for running durable stateful AI agents, requiring self-hosting rather than a fully managed cloud. Agent 37 records 180,030 monthly visits with +24.2% month-over-month growth and Free Trial, Contact for Pricing pricing. Rivet.dev records 21,359 monthly visits with -44.3% growth and Freemium, Contact for Pricing pricing.
The low-cost cloud sandbox where AI agents actually live
Run and scale durable AI agents on your own infrastructure
| Dimension / Metric | | |
|---|---|---|
| Official Domain | agent37.com | rivet.dev |
| Pricing Model | Free Trial, Contact for Pricing | Freemium, Contact for Pricing |
| Monthly Visits | 180.03K (180,030) | 21.36K (21,359) |
| MoM Traffic Delta | +35.12K (+24.2%) | -16.97K (-44.3%) |
| Primary Market & Share | 🇵🇾 Paraguay (52.6%) | 🇺🇸 United States (39.4%) |
| Direct Visits / mo | 72.67K | 10.71K |
| User Rating | 4.3 | 4.5 |
| Supported Platforms | Website | Website |
The low-cost cloud sandbox where AI agents actually live
Pay for vCPU, memory and disk separately while the sandbox runs; when it sleeps or is deleted the compute meter stops and you are left with disk cost only.
Launch Claude Code, Codex, OpenClaw, OpenCode, Hermes, Grok or your own Docker image, each in its own tenant-isolated sandbox.
Files survive sleep, restarts and weeks of inactivity, and agents can be attached to cron-style schedules so work runs unattended.
Expose individual ports publicly, attach your own domain, or keep everything behind an API key on an authenticated URL.
Run and scale durable AI agents on your own infrastructure
Every Actor gets a SQLite database and a filesystem, so an agent's memory and progress survive restarts and idle periods without a separate database.
Run untrusted or AI-generated code on your own infrastructure with fine-grained control over network access, filesystem permissions, and resource limits.
A node failure reschedules its Actors elsewhere with state intact, and multi-step work replays after a crash — with no checkpointing harness to build yourself.
Address an Actor directly over HTTP or hold a live WebSocket, and use the React SDK to subscribe components to an Actor's state in real time.
SpecialistThe AI developer cloud for GPU pods, serverless inference and clustering
SpecialistThe AI developer cloud for GPU pods, serverless inference and clustering
SpecialistRuns serverless Python containers optimized for AI model inference and batch jobs rather than persistent agent sandboxes.
SpecialistRuns serverless Python containers optimized for AI model inference and batch jobs rather than persistent agent sandboxes.
Free / Open-sourceThe TypeScript framework for building, deploying, and observing AI agents
SpecialistCloud browsers and web APIs for AI agents
SpecialistCloud browsers and web APIs for AI agents
Self-hosted cloud development environments and AI coding agents for enterprise teams
SpecialistLow-cost cloud GPUs with per-minute instances and per-second sandboxes for AI workloads.
SpecialistLow-cost cloud GPUs with per-minute instances and per-second sandboxes for AI workloads.
Persistent Ubuntu cloud VMs built for AI agent factories
Agent-native cloud infrastructure that lets coding agents run the whole backend stack
Cloud Linux VMs built for developers and their AI agents
Cloud Linux VMs built for developers and their AI agents
Free / Open-sourceBuild, run and scale AI, from open models to governed agents
Free / Open-sourceProduction cloud on autopilot for full-stack and AI apps
Free / Open-sourceProduction cloud on autopilot for full-stack and AI apps
Free / Open-sourceDeploy anything, own everything
