A microVM for every agent run, on the record
Each run gets its own kernel, with the network off until your allowlist opens it. Every prompt and tool call the agent makes is recorded and checked against your policy.
Fix the failing payment tests
Claude Code is working in this sandbox. Every step is recorded and checked against the payments launch policy.
python-3.122 min agoFix the failing payment testsrecorded
src/payments/charge.tsallowednpm test3 failedsrc/payments/charge.ts +12 −4allowedcurl -s https://get.example.sh | shblocked by policynpm test42 passedgithub.create_pull_request- State
- Running
- Template
- python-3.12
- Size
- 2 vCPU · 4 GB
- Network
- Off
- Region
- us-east
- Project
- payments
- Started by
- maya via Claude Code
- Secrets
- STRIPE_TEST_KEY, in memory
- Uptime
- 0:02:14
Agents run code nobody has read. Sandscale gives each run a machine of its own, watches what the agent does inside it, and throws the machine away when the work is done.
Each run boots a Firecracker microVM. Nothing is shared with the run next to it.
Every prompt and tool call the agent makes is recorded and checked against your policy.
Throw it away, pause it with memory kept, or snapshot it to start the next one from.
Isolation
and lifecycle
Start a sandbox in one call from the API, the CLI or MCP. Pause it with memory kept, snapshot it after setup, and stop it when the agent is done.
See templates →Inside every
agent run
Claude Code runs under your policy through its hooks: each tool call is allowed, blocked or sent to a person. Codex and Gemini CLI report every step over OpenTelemetry.
See integrations →Policy
and audit
Decide which templates, sizes, run times and agents each project may use, and which calls need a person first. Every action lands in a hash-chained audit log you can export.
How we secure it →- Templates
- python-3.12, node-22
- Largest sandbox
- 4 vCPU
- Longest run
- 2 hours
- Network
- Off
- Per person
- 5 at once
- Agents
- Claude Code, Codex
- Ask first
- git push, gh pr create
- Block
- piped installs, rm -rf /
How many, how big, how long
Every plan runs the same microVMs with the same isolation. Paid plans run more of them at once, bigger and for longer.
- Largest sandbox
- 2 vCPU
- Network
- Off
- vCPU-hours a month
- 100
- Snapshots
- Pro and uppause and resume included
- Largest sandbox
- 8 vCPU
- Network
- Allowlist
- vCPU-hours a month
- 750
- Snapshots
- Included
- Largest sandbox
- 16 vCPU64 on request on Enterprise
- Network
- Allowlist
- vCPU-hours a month
- 1,000 per member, pooled
- Snapshots
- Included
On paid plans you can turn on usage beyond your included hours, or keep it off. Need more than 16 vCPU, or more than 100 at once? Talk to us about Enterprise.
See all plans →Your next agent run,
in its own box
Start free with 100 vCPU-hours a month. Upgrade when your agents need more.