OpenComputer
Persistent cloud Linux VMs for long-running agents that hibernate and wake, with checkpoints, regions and a serverless-agent harness on top. Choose it when agents need a machine that persists and wakes, and you are comfortable with pool-based pricing and an evolving agent-first API.
Overview
OpenComputer, from the team behind the diggerhq GitHub organisation, sells persistent cloud Linux VMs for agents and positions them against stateless sandboxes: each machine is a full VM with its own filesystem and OS access that stays on, hibernates when idle and wakes on demand. On top of the VMs sits a "serverless agents" harness in which agents are TypeScript functions deployed with the opencomputer CLI, with durable sessions, schedules, webhooks, cross-session memory, a per-project SQL database and Slack, GitHub and Linear connections. There are TypeScript and Python SDKs and a Management API.
Checkpoints can be forked or restored, VMs can be resized at runtime and sandboxes can be pinned to one of about twenty regions. Pricing is by machine pool rather than per second: a free shared tier, Medium at $300/month and Large at $3,000/month. The repository is Apache-2.0 and includes a SELFHOSTING.md that describes an "operator path" running worker VMs on QEMU/KVM with PostgreSQL, Redis and S3-compatible storage on AWS or Azure, rather than a one-command install. Hibernate/wake timings, GPU support and compliance are not documented.
Notable
- Repository has 587 GitHub stars and is Apache-2.0; self-hosting is described as "an operator path, not a one-command hosted product".
- Blog post "Scaling one VM to a million sandboxes" (2026) mentions per-second billing from 10-second heartbeats; the published plans are monthly machine pools.
- Comparison pages target coding-agent products (Claude Code on the web, Codex cloud, Devin) rather than sandbox SDKs.
OpenComputer specifications
| Attribute | Details |
|---|---|
| Isolation | Full Linux VM per sandbox; the self-hosting guide names QEMU/KVM, the website does not name the hypervisor |
| Deployment | Hosted platform · Self-hostable |
| Open source | Yes (Apache-2.0) |
| SDKs and interfaces | JavaScript/TypeScript, Python, CLI, REST API |
| Cold start (vendor claim) | Not documented |
| Max session length | No limit documented; VMs are described as always on, with hibernate and wake |
| Persistence | VMs keep state across sessions and can hibernate and wake; "instant snapshots" with fork or restore to any point; CPU and memory resizable at runtime; files under /workspace are kept in a versioned S3-backed workspace |
| GPU | Not documented |
| Networking | Open internet by default; an [egress] allowlist of up to 64 domains (HTTPS only) and 64 IPs/CIDRs can be set per agent; fixed outbound IPs per region; preview URLs with Clerk auth and custom domains |
| Pricing | Free: shared up to 2 vCPU and 2 GB, 3 GB disk, 5 concurrency. Medium $300/month: 8 CPU, 16 GB, 50 GB disk, 50 concurrency. Large $3,000/month: 64 CPU, 512 GB, 3,800 GB disk, 500 concurrency. Custom: contact |
| Free tier | Free tier: shared up to 2 vCPU and 2 GB memory, 3 GB disk, 5 concurrency |
| Compliance | Not documented |
| Regions | Selectable per agent: broad us, eu, ap plus sub-regions such as us-east, eu-west, uk, jp, au, ca, mx, me, sa and af; default is wherever capacity is available, usually the US |
Facts from OpenComputer’s public documentation, verified November 9, 2026. Performance numbers are vendor claims.
Strengths and trade-offs
Strengths
- You want a VM that keeps state for days and hibernates rather than a sandbox that expires.
- You need region pinning with fixed egress IPs for allowlisting on the other end.
- You are building an agent product and want sessions, schedules, webhooks and memory handled for you.
- You want an Apache-2.0 codebase you could run yourself with enough operations effort.
Trade-offs
- The website does not name the hypervisor; QEMU/KVM appears only in the self-hosting guide.
- No hibernate/wake timing, GPU or compliance information is published.
- Pricing is by monthly machine pool, so short bursty workloads pay for idle capacity.
- The product is framed around its own agent harness; using the VMs with another harness is less documented.
Good fit for: B2B agent platforms that give each user or agent a persistent Linux VM rather than a disposable sandbox.
How OpenComputer compares
| Sandbox | Isolation | Open source | Self-host / BYOC | Cold start (vendor) | Max session | Snapshots / pause | GPU | SDKs |
|---|---|---|---|---|---|---|---|---|
| OpenComputer | QEMU/KVM VM | Yes | Yes / No | Not documented | No limit documented | Yes / Yes | Not documented | JavaScript/TypeScript, Python, CLI, REST API |
| exe.dev | VM (VMM per VM) | No | No / Yes | ~1 s (claim) | No cap | Yes / Not documented | Not documented | CLI (over SSH), HTTPS API, MCP server |
| Fly.io Sprites | MicroVM | No | No / No | 0.1–2 s wake | Unlimited | Yes / Yes | No | JavaScript/TypeScript, Go, Python, Elixir |
| Superserve | Firecracker microVM | No | No / Yes | Not documented | Unlimited | Yes / Yes | Not documented | Python, JavaScript/TypeScript, CLI, REST API, MCP server |
| Islo | MicroVM (hypervisor not named) | No | No / Yes | Not documented | Policy-driven | Yes / Yes | Not documented | CLI, REST API |
| Daytona | Containers or VMs | No | Not documented / Yes | <90 ms | Unlimited | Yes / Yes | Yes | Python, TypeScript, Ruby, Go, Java |
Frequently asked questions
What is OpenComputer?
How does OpenComputer isolate code?
Is OpenComputer open source?
How much does OpenComputer cost?
What are the alternatives to OpenComputer?
Sources
Cite this page
Agent Sandboxes. (2026). OpenComputer. agentsandboxes.org. Last reviewed November 9, 2026. https://agentsandboxes.org/sandboxes/opencomputer/
Found an error or a missing sandbox? Submit a correction — every entry links to the sources it relies on.