Isorun
$19.36 a month*
Home / AI agent sandboxes / Promigence
Sandboxes for agents, evals and CI from verified snapshots, billed per second with a quote and hard spend cap per run.
Verdict (2026-11-13): Promigence scores 55/100, #52 of 63 AI agent sandboxes. Strong on persistence, docs and SDKs. Weak on isolation. Best for: Evaluation and RL runs that fork many identical sandboxes and need environment failures kept apart from agent failures.
Skip it if: Free accounts are limited to 1-hour sessions and 20 sandboxes at once.
Prices checked 2026-11-15.
Promigence starts sandboxes from snapshots that must pass their own verify command at build time, and forks many identical copies at once for agent runs, evaluations, RL rollouts and CI jobs. Usage is metered per second at $0.0504 per vCPU-hour and $0.0162 per GiB-hour, paused time is not billed, and snapshot storage and egress are included. Every run is priced before it starts and held to a hard spend cap, and runs report environment failures separately from task failures. New accounts get $50 of free credit; paid plans are arranged by email.
55/100 in AI agent sandboxes, rank 52 of 63. Parts with no data are left out and the rest is rescaled.
Full Promigence pricing: plans and costs at four workloads →
$19.36 a month*
$11.73 a month*
$10.14 a month*
$19.00 a month*
$17.95 a month*
$28.44 a month*
$20.00 a month*
$20.00 a month*
Promigence is not in the public benchmarks we track yet. See all benchmarks.
| Promigence | |
|---|---|
| Category | agent sandbox |
| Our score | 55/100 |
| Isolation | Isolated sandbox per run; the isolation technology is not stated |
| vCPU per hour | $0.0504 |
| Memory per GiB-hour | $0.0162 |
| Storage per GiB-month | $0.00 |
| Billing | per second (1-second minimum) |
| Free tier | $50 of free credit to start; the owner claims it once in the browser. |
| Pause and resume | Yes |
| Snapshots | Yes |
| GPU | No |
| Custom images | Yes |
| Network controls | Yes |
| Max vCPU | 8 vCPU |
| Max memory | 32 GiB |
| Open source | No |
| Self-host | No |
| SDKs and interfaces | JavaScript/TypeScript, Python, CLI, MCP server, REST API |
| Regions | Not stated on the pages checked; the API reports a location code such as us-east. |
| Facts checked | 2026-11-13 |
No reviews yet. Have you used Promigence? Your review helps other developers choose.
Promigence scores 55/100, #52 of 63 AI agent sandboxes. Strong on persistence, docs and SDKs. Weak on isolation. Best for: Evaluation and RL runs that fork many identical sandboxes and need environment failures kept apart from agent failures. Facts checked 2026-11-13.
$29.15 a month for 2 vCPU, 4 GiB, 176 hours a month (8 h × 22 days), CPU busy 30%. Free tier: $50 of free credit to start; the owner claims it once in the browser.
Isolated sandbox per run; the isolation technology is not stated.
In AI agent sandboxes, the top-rated are Isorun (78/100), Northflank (78/100), Koyeb Sandboxes (76/100). Promigence is #52 of 63.
Metered per second at $0.0504 per vCPU-hour plus $0.0162 per GiB-hour
$0.000046 per second ($0.1656 per hour)
Plans are set up with you by email.
20 sandboxes at once, sessions up to an hour
Snapshot storage: Included. Included in every plan.
A paused environment accrues nothing, and nothing accrues before one is handed to you.
5× the usage of Pro, or 20× for $500
A new account runs 20 sandboxes at once, each for up to an hour (15 minutes unless `--timeout` asks for more), on sizes up to large (8 vCPU), with 20 GB of data out a month.
It is kept for 30 days, and resuming it starts the 30 days again.
No sandbox can see, reach or address another, yours or anyone else's.
A new account's owner claims its free credit once, in the browser
There are no GPUs or Windows images.