HomeBlogPricingCareersDocsGitHubSlack community

Sandbox-native cloud for agents.

Stateful compute for durable agentic loops + isolated tool/code execution. Pause mid-run, resume hours later in the exact state you left.

Free tier included. No credit card required.

● RUNNING
import { Sandbox } from "tensorlake";

async function main() {
const sbx = await Sandbox.create();
const result = await sbx.run("/bin/sh", { args: ["-c", "npm install && npm run build"] });
console.log(result.stdout);
}
main();
$npx tsx sandbox.tsRAN
✓ sandbox created sbx_rhcj28c · tensorlake/ubuntu-minimal · 460 ms
✓ npm install (143 pkgs) · 1.7 s
✓ npm run build · compiled in 4.8 s
EXECUTION ENVIRONMENTS01 / 06

Give your agent a computer.

PATTERNS
harness · tool

Run persistent sandboxes that give an agent its own computer, or spin up ephemeral ones to isolate each tool call.

ISOLATED RUNTIME

Give the agent its own filesystem, shell, packages, and processes instead of sharing the app server runtime.

STATEFUL BY DEFAULT

Sandboxes sleep on inactivity and wake instantly when invoked — sessions can run for hours or days.

REAL SOFTWARE STACKS

Compile code, run databases, process large files. Bring any Linux stack.

RUN TOOL CALLS SAFELY

Execute LLM-generated code inside secure microVMs, isolated from the harness.

SNAPSHOT · RESUME · COPY02 / 06

Suspend, resume, and copy a whole machine.

LIFECYCLE
suspend · resume · fork
SUSPEND · RESUME

Pause on idle. Wake in a second.

Freeze a sandbox — memory, processes, and filesystem intact — and the meter stops. Resume by name in about a second, or let it wake automatically the moment a request or connection comes in.

LIFECYCLE · CLItl sbx
$ tl sbx suspend my-dev
✓ suspended · meter stopped · state on disk
$ tl sbx resume my-dev
✓ resumed in 0.9s · pid 4127 still alive
↺ auto-wakes on the next request or connection
COPY · FORK THE VM

Fork a running VM, memory and all.

Clone a live sandbox — its memory and filesystem copied whole — then run the copies. A fork of the entire machine: build a base once, then fan out identical copies to run many CI jobs in parallel.

COPY · CLItl sbx copy
$ tl sbx copy build-base --count 8
✓ forked 8 copies (memory + filesystem)
build-base-01 … build-base-08 running
$ tl sbx ls --tag build-base
8 sandboxes · 0 cold starts · ready for jobs
BENCHMARKS03 / 06

The fastest sandbox file system.

METHOD
fio · sqlite · p50

SQLite benchmark — 2 vCPU, 4 GB RAM, 100k inserts

View benchmark on GitHub
Tensorlake
2.45s1.0×
Vercel
3.00s1.2×
E2B
3.92s1.6×
Modal
4.66s1.9×
Daytona
5.51s2.2×
FSYNC4.1×
SEQ WRITE2.8×
RAND READ1.9×
COLD START84ms

In our published SQLite benchmark across Tensorlake, Vercel, E2B, Daytona, and Modal, Tensorlake was the fastest across default, fsync, and large-dataset runs. Benchmark setup: 2 vCPU / ~4 GB sandboxes, 3 runs.

HARBOR · EVALS & RL04 / 06

Harbor integration for agents evals and RL rollouts.

BENCH
terminal-bench@2.0
01

Prepare once, clone many

Snapshot a warmed environment — deps, weights, data — and clone it thousands of times in parallel. Pay once for setup.

02

Known starting state

Files, packages, processes and seeds are reproducible across every rollout. No flakey drift across workers.

03

Scale rollouts & evals

Fan out to 10k+ concurrent environments. Checkpoint at any step, resume at any step, write to object storage.

HARBOR · RUNterminal-bench@2.0
#  from an OCI image
harbor run --env tensorlake \
  --ek use_oci_image_build=true \
  --dataset terminal-bench@2.0 \
  --agent claude-code \
  --model anthropic/claude-opus-4-8 \
  --ae ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY

# from a snapshot
harbor run --env tensorlake \
  --ek snapshot_id=snap_abc123 \
  --dataset terminal-bench@2.0 \
  --agent claude-code \
  --model anthropic/claude-opus-4-8
OUTPUT● 0.921
terminal-bench • oracle
┏━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━┓
┃ Trials ┃ Exceptions ┃  Mean ┃
┡━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━┩
│     89 │          0 │ 0.921 │
└────────┴────────────┴───────┘

┏━━━━━━━━┳━━━━━━━┓
┃ Reward ┃ Count ┃
┡━━━━━━━━╇━━━━━━━┩
│ 0.0    │     7 │
│ 1.0    │    82 │
└────────┴───────┘

Job Info
Total runtime: 20m 54s
ORCHESTRATION05 / 06

Sandbox-native orchestration for agents.

LAYER
endpoints · durability
[ 06.1 ] · ORCHESTRATE

Once sandbox usage turns into a real application, Orchestrate coordinates it.

The layer that adds application endpoints, durability, fan-out, retries, and application-level observability on top of sandbox execution.

APPLICATION ENDPOINTS

Expose sandbox-backed workflows as callable applications instead of stitching together raw VM APIs.

DISTRIBUTED FAN-OUT

Predictable throughput means fresh sessions spin up immediately, even when a thousand others are mid-task.

WAKE ON REQUEST

Dormant sandboxes resume on incoming traffic. Every session gets its own sandbox so nothing leaks across runs.

QUEUES, TIMERS, AND RETRIES

Durable primitives for long-running agentic flows. Application observability baked in.

ORCHESTRATE · APP | doc-to-md$ tl app deploy
# PDF → Markdown with Claude
from tensorlake.applications import application, function
from anthropic import Anthropic

claude = Anthropic()

@application()
@function()
def to_markdown(pdf_url: str) -> str:
pdf = fetch(pdf_url)
msg = claude.messages.create(
model="claude-sonnet-4-5",
max_tokens=8192,
messages=[{"role": "user", "content": [
{"type": "document", "source": pdf},
{"type": "text", "text": "Convert to clean Markdown."},
]}],
)
return msg.content[0].text
REMOTE DEV06 / 06

SSH in from any machine. The sandbox is your dev environment too.

ACCESS
ssh · vs code · pty

A named sandbox isn't only an execution surface — it's a portable cloud workstation. Register your key once, then ssh in, or open it in VS Code, Cursor, or JetBrains Gateway over Remote-SSH. scp, rsync, and full port-forwarding all ride the same connection.

PORTABLE IDENTITY
Connect to the same sandbox id from any laptop. Which region or host the VM lives on is the platform's problem — not yours.
SUSPEND ON IDLE
Named sandboxes auto-suspend after the idle timeout. The clock pauses while you're connected, so you only pay while you work.
STATE SURVIVES RESUME
Filesystem, memory, running processes, tmux sessions and ~/.vscode-server are exactly where you left them — resume by name, weeks later.
PTY OVER WEBSOCKET
Building a browser terminal? Drive a programmatic PTY over WebSocket, disconnect, and reattach to the same session by token.
REMOTE DEV · WALKTHROUGH● 0:45
LOCAL — ZSH
~/PROJECTS/TENSORLAKE
tensorlake
CUSTOMER SIGNAL07

Used by engineering teams shipping agents in production.

SAMPLE
n = 14 interviews

Tensorlake let us ship faster and stay reliable from day one. Complex stateful AI workloads that used to require serious infra engineering are now just long-running functions. As we scale, that means we can stay lean — building product, not managing infrastructure.

AB
Arpan BhattacharyaCEO, The Intelligent Search Company

At SIXT, we're building AI-powered experiences for millions of customers while managing the complexity of enterprise-scale data. Tensorlake gives us the foundation we need — reliable document ingestion that runs securely in our VPC to power our generative AI initiatives.

BD
Boyan DimitrovCTO, Sixt

Tensorlake enabled us to avoid building and operating an in-house OCR pipeline by providing a robust, scalable OCR and document ingestion layer with excellent accuracy and feature coverage.

YS
Yaroslav SklabinskyiPrincipal Software Engineer, Reliant AI

With Tensorlake, we've been able to handle complex document parsing and data formats that many other providers don't support natively, at a throughput that significantly improves our application's UX. The team's responsiveness stands out.

VD
Vincent Di PietroFounder, Novis AI
BACKED BY
DEPLOY & TRUST08

Run it in our cloud — or yours.

COMPLIANCE
SOC 2 · HIPAA
[ 08 ] FOR TEAMS OUTGROWING SAAS

Bring Tensorlake into your cloud.

Run sandboxes and applications inside your own AWS / GCP / Azure account when you need lower egress, stricter network boundaries, dedicated capacity or more predictable performance.

01
Network boundariesKeep code and data inside your preferred cloud boundary. VPC peering, private endpoints, IAM-scoped.
02
Latency controlCompute closer to data. Tighten runtime behavior for latency-sensitive agent workloads.
03
Reserved capacityMove from usage-based hosted infra to capacity you plan, reserve, and operate predictably.
[ 09 ] SECURITY

Security built for agentic workflows.

LLM-generated code runs in isolated VMs, not shared processes. Full audit trails, per-project data boundaries, and compliance for regulated workloads.

01
Firecracker isolationEach tool call and harness runs in its own microVM. No shared kernel, no cross-tenant state.
02
Tracing & observabilityFull traces of every function and tool call — logs, timing, structured execution paths.
03
SOC 2 Type II · HIPAASecure by default for PHI, PII and sensitive documents. Isolated buckets with RBAC and full audit.
▪ THE DOCUMENT DIGEST · WEEKLY

Subscribe for release notes, benchmarks, deep dives.

~ 3,400 ENGINEERS. MONTHLY. NO SPAM.
▪ THE INFRASTRUCTURE LAYER FOR AGENTS

Ship agents faster
with Tensorlake.

$pip install tensorlake #  or:  npm i @tensorlake/sdk