Sailboxes
$8.36 a month*
Home / Dev boxes for AI agents / Tembo
Agent orchestration platform that runs each coding session in its own Linux VM, billed per vCPU and GiB.
Verdict (2026-11-14): Tembo scores 58/100, #27 of 38 dev boxes for AI agents. Strong on isolation, docs and SDKs. Best for: Teams that want agents triggered from issue trackers, alerts and chat, with each session in its own VM.
Skip it if: VMs are only available inside Tembo sessions; there is no standalone sandbox product.
Prices checked 2026-11-15.
Tembo runs coding agents such as Claude Code, Codex, Cursor, Amp and OpenCode on tasks from GitHub, Linear, Slack, Sentry and other tools, with each session in a dedicated Linux VM. VM compute is metered per second at $0.0403 per vCPU-hour plus $0.0130 per GiB-hour while the VM runs, and draws from a monthly dollar allowance that also covers model calls through Tembo's own gateway. Paid plans include more usage than their fee and allow optional overage billing with a spend limit. Sandboxes are set up per session and torn down when it ends, apart from cached project environments.
58/100 in dev boxes for AI agents, rank 27 of 38. Parts with no data are left out and the rest is rescaled.
$8.36 a month*
$24.20 a month*
$19.36 a month*
$16.46 a month*
$20.00 a month*
$20.00 a month*
$41.80 a month*
$20.00 a month*
Tembo is not in the public benchmarks we track yet. See all benchmarks.
| Tembo | |
|---|---|
| Category | dev box, coding agent |
| Our score | 58/100 |
| Isolation | Dedicated Linux VM per session, with nested virtualization for Docker |
| vCPU per hour | $0.0403 |
| Memory per GiB-hour | $0.013 |
| Billing | per second |
| Free tier | 7-day free trial of the Max plan with an included usage allowance (amount not stated), up to 10 users and VM size up to XL. Sessions stop when the trial or its allowance ends; no overage billing during the trial. |
| Snapshots | Yes |
| Max vCPU | 16 vCPU |
| Max memory | 32 GiB |
| Open source | No |
| Self-host | Yes |
| SDKs and interfaces | TypeScript, REST API, MCP |
| Regions | Not stated on the pages checked; self-hosted and VPC deployment are offered for organizations. |
| Facts checked | 2026-11-14 |
No reviews yet. Have you used Tembo? Your review helps other developers choose.
Tembo scores 58/100, #27 of 38 dev boxes for AI agents. Strong on isolation, docs and SDKs. Best for: Teams that want agents triggered from issue trackers, alerts and chat, with each session in its own VM. Facts checked 2026-11-14.
$60.00 a month for 2 vCPU, 4 GiB, 220 hours a month (10 h × 22 days), CPU busy 20%, paused the rest of the time. Free tier: 7-day free trial of the Max plan with an included usage allowance (amount not stated), up to 10 users and VM size up to XL. Sessions stop when the trial or its allowance ends; no overage billing during the trial.
Dedicated Linux VM per session, with nested virtualization for Docker.
In dev boxes for AI agents, the top-rated are Sailboxes (86/100), Isorun (79/100), Tensorlake Sandboxes (78/100). Tembo is #27 of 38.
$0.0403 / vCPU-hour
$0.0130 / GiB RAM-hour
Metered by the second at the equivalent rate. Stopped and snapshotted VMs do not accrue compute charges.
Includes $90 in usage every month
Includes $400 in usage every month
Start with a 7-day free trial of Max.
Pro ($60/month): $90 monthly usage allowance, up to 5 users, sandbox size up to medium, with overage billing
Tembo measures each running VM in seconds and bills its actual running time at the per-second equivalent of the hourly rate.
Each session runs in a dedicated Linux VM, and no two sessions share the same VM.
Sandboxes are ephemeral: spun up for the session, destroyed when it's done.
Pro goes up to Medium. The Max plan goes up to XL. XXL and Ultra are available on request.
| Ultra | 32 | 128 GB | 200 GB |
Reusable snapshots, setup and pre-run scripts, adjustable compute, and on-demand VM keep-alive