Infrastructure for AI Agents

Give your agenta machine to Live

Secure, isolated sandboxes where AI agents run code, browse the web, and ship to production — all from one API.

Works with
OpenClaw
AutoGPT
LangChain
CrewAI
Cursor
Devin
oblien — terminal
zsh
Latency190ms
Regionus-east
oblien sdk v2.0
<200ms
Cold start
99.9%
Uptime
Sandbox lifetime
Scroll to explore

Everything an agent needs to operate

Machines, tools, and networking — raw primitives with zero abstraction tax.

Code Execution

Run Python, Node.js, Bash, and more in isolated containers with full stdin/stdout streaming.

Browser Automation

Headless Chrome instances for web scraping, testing, and autonomous browsing tasks.

Persistent Storage

Filesystem persistence across sessions. Agents can read, write, and manage files like a real workstation.

Real-Time Streaming

WebSocket-based output streaming. Watch your agents think and execute in real-time.

Network Control

Fine-grained network policies per sandbox. Allow, deny, or proxy specific endpoints.

Multi-Tenant Isolation

Run agents for multiple customers with full resource and data isolation between tenants.

A Machine to Live In

Full Linux sandboxes with filesystem, networking, and process isolation. Ephemeral for one-off tasks, persistent for agents that need a home.

Tools to Work With

Shell execution, file I/O, browser automation, web search — raw primitives your agents compose into autonomous workflows.

A Way to Ship

Turn any sandbox into a live deployment with one API call. Custom domains, SSL, and edge routing — from prototype to production instantly.

The Platform

Where AI agents
come alive.

Your agent deserves more than an API call. Give it a living environment — a sandbox that boots, runs, persists, connects, and ships to the world.

Execute
Any language
Browse
The open web
Store
Persistent files
Connect
Full network
Ship
Go live instantly
Inspect
SSH anytime
oblienSANDBOX

A place to live

Isolated sandbox per agent — always on, always ready.

Everything built in

Code, browse, files, network — one SDK, zero setup.

Go live instantly

Deploy with custom domains, SSL, and routing in one call.

Observe everything

Logs, metrics, and SSH access — full visibility into every agent session.

What You Can Build

Built for every use case

Real use cases. Real infrastructure. Agents that don't just reply — they operate.

Personal Agent

Run any agent — securely in the cloud

Deploy open-source agents like OpenClaw, AutoGPT, or your own — each gets a secure, isolated cloud sandbox with full power. Persistent memory, unrestricted networking, browser access, and real compute. Your agent runs 24/7 without touching your local machine.

24/7
Uptime
Full
Isolation
All
Tools
Works with
OpenClaw
AutoGPT
LangChain
CrewAI
Run any open-source agent
Persistent memory & files
Secure cloud sandboxes
oblien — personal
Persistent
Uptime24/7
IsolationFull
ToolsAll
oblien sdk v2.0
Every sandbox includes
Linux OS
Shell Access
Filesystem
Browser
Search API
Networking
SSH
Deploy
Build Your Way

Code it or click it

Full SDKs for Python, JavaScript, and Go — or deploy agents straight from the dashboard. Your call.

oblien-sdk
from oblien import Sandbox

# Create a persistent sandbox for your agent
sandbox = Sandbox.create(persistent=True, memory="4GB")

# Your agent runs code, browses, stores files
result = sandbox.exec("python agent.py --task research")
sandbox.fs.write("/data/report.md", result.output)

# Deploy to a live URL when ready
url = sandbox.publish(port=3000, domain="my-agent.oblien.app")

# Or just SSH in to inspect
sandbox.ssh()  # → root@sandbox-3d1b:~$
4
SDKs
<50ms
Latency
100%
API Coverage
OSS
Open Source
oblien.com/dashboard/deploy
4 GB
Persistent
my-agent.oblien.app
ShellBrowserFilesNetworkSSH

Deploy any open-source agent in seconds — no code required.

Full System Access

Your agent gets an entire machine

Not a restricted API. Not a thin wrapper. A full Linux system with shell, filesystem, network, and browser — all programmable through one unified SDK.

Your Agent
LLM + Logic
Reasoning, planning, tool-calling. Your code controls the flow.
connected
Oblien SDK
One interface. Full system access.
v2.0
Shell.exec()
Files.fs.*
Browser.browser.*
Network.http.*
Publish.publish()
Firewall.network.*
Search.search()
Streaming.stream()
Snapshots.snapshot()
Isolated Sandbox
Full Machine
Linux OS
Root access
Network stack
Persistent disk

Full Operating System

Real Linux with root. Install anything, run services, manage processes.

apt/pip/npmsystemdRoot access

Filesystem & Persistence

Read, write, manage files. Persistent volumes that survive restarts.

Read/WriteVolumesUpload/Download

Publish to the World

Ship instantly. One call to publish any port to a live URL with auto SSL.

One-clickCustom domainsAuto SSL

Advanced Firewall

Granular network control per sandbox. Allow/block domains, IPs, ports.

AllowlistsIP rulesAudit logs

Browser API + Proxies

Headless browser with rotating proxies. Scrape and extract at scale.

Headless ChromeProxiesAnti-detection

Full Operating System

Real Linux with root. Install anything, run services, manage processes.

apt/pip/npmsystemdRoot access

Filesystem & Persistence

Read, write, manage files. Persistent volumes that survive restarts.

Read/WriteVolumesUpload/Download

Publish to the World

Ship instantly. One call to publish any port to a live URL with auto SSL.

One-clickCustom domainsAuto SSL

Advanced Firewall

Granular network control per sandbox. Allow/block domains, IPs, ports.

AllowlistsIP rulesAudit logs

Browser API + Proxies

Headless browser with rotating proxies. Scrape and extract at scale.

Headless ChromeProxiesAnti-detection

Search API

Web search and content extraction. Search, extract, and process in one call.

Web searchExtractionPDF parsing

Real-Time Streaming

WebSocket connections for live output. No polling, no delays.

WebSocketsLive outputEvents

Network & HTTP

Outbound requests, run servers, expose ports. Full networking stack.

HTTP/HTTPSPort exposureDNS

Multi-Agent Orchestration

Multiple sandboxes in parallel. Spawn sub-agents, share data, coordinate.

ParallelShared volumesWorkflows

Full Operating System

Real Linux with root. Install anything, run services, manage processes.

apt/pip/npmsystemdRoot access

Filesystem & Persistence

Read, write, manage files. Persistent volumes that survive restarts.

Read/WriteVolumesUpload/Download

Publish to the World

Ship instantly. One call to publish any port to a live URL with auto SSL.

One-clickCustom domainsAuto SSL

Advanced Firewall

Granular network control per sandbox. Allow/block domains, IPs, ports.

AllowlistsIP rulesAudit logs

Search API

Web search and content extraction. Search, extract, and process in one call.

Web searchExtractionPDF parsing

Real-Time Streaming

WebSocket connections for live output. No polling, no delays.

WebSocketsLive outputEvents

Network & HTTP

Outbound requests, run servers, expose ports. Full networking stack.

HTTP/HTTPSPort exposureDNS

Multi-Agent Orchestration

Multiple sandboxes in parallel. Spawn sub-agents, share data, coordinate.

ParallelShared volumesWorkflows

Full Operating System

Real Linux with root. Install anything, run services, manage processes.

apt/pip/npmsystemdRoot access

Filesystem & Persistence

Read, write, manage files. Persistent volumes that survive restarts.

Read/WriteVolumesUpload/Download

Publish to the World

Ship instantly. One call to publish any port to a live URL with auto SSL.

One-clickCustom domainsAuto SSL

Advanced Firewall

Granular network control per sandbox. Allow/block domains, IPs, ports.

AllowlistsIP rulesAudit logs

Everything a developer would do on their own machine — now available to your agent via a single API call.

Flexible Environments

One sandbox, infinite lifetimes

Temporary for a task. Persistent for an agent. Deployed to the world. Every sandbox adapts to what your agent needs right now.

Spin up. Run. Destroy.

Temporary sandboxes for one-off tasks. Your agent gets a fresh environment, executes its job, and the sandbox self-destructs. Zero cleanup, zero cost when idle.

Auto-cleanupCost-efficientTask-scopedParallel-safe
ephemeral — sandbox terminal
$ sandbox = Sandbox.create(timeout="10m")
→ sandbox-8f2a ready (312ms)
$ sandbox.exec("python analyze.py --data input.csv")
→ Analysis complete. Results saved.
$ # sandbox auto-destroys after timeout

Stop Duct-Taping Infrastructure

Most teams waste months building sandbox infra. We ship it as one import.

DIY Approach~26 weeks
Container orchestration
~6 wks
Code execution layer
~4 wks
Security isolation
~5 wks
Tool integrations
~4 wks
Deployment pipeline
~3 wks
Multi-tenant isolation
~4 wks
vs
Oblien~5 min
Isolated sandboxes via API
.create()
Execute code in any language
.exec()
Built-in tool primitives
.tools.*
Deploy with one call
.deploy()
SSH into any sandbox
.ssh()
Scale without thinking
.namespace
26 weekssaved
1 importto replace it all
$0to start
Simple Pricing

Pay for what you use. Nothing more.

Start free, scale as you grow. No hidden fees, no surprise bills. Every plan includes full access to all APIs and tools.

Starter

For experimenting and building prototypes

Free
  • 5 sandbox hours / month
  • 1 concurrent sandbox
  • 512MB memory per sandbox
  • Browser API (100 req/day)
  • Search API (50 req/day)
  • Built-in per-user tracking
  • Community support
Most Popular

Pro

For shipping production agents

$29/mo
  • 100 sandbox hours / month
  • 10 concurrent sandboxes
  • 4GB memory per sandbox
  • Browser API with proxies
  • Search API (unlimited)
  • Persistent storage (10GB)
  • Namespace user management
  • Per-user usage analytics
  • Custom domains & publish
  • Priority support

Scale

For teams running agents at scale

$149/mo
  • 1,000 sandbox hours / month
  • 50 concurrent sandboxes
  • 16GB memory per sandbox
  • All APIs unlimited
  • Persistent storage (100GB)
  • Advanced namespace controls
  • Per-user billing & limits
  • Advanced firewall controls
  • Multi-agent orchestration
  • Dedicated support + SLA

Enterprise

For organizations with custom needs

Custom
  • Unlimited sandbox hours
  • Unlimited concurrency
  • Custom resource limits
  • Dedicated infrastructure
  • Full namespace white-label
  • Custom per-user policies
  • VPC peering & private networks
  • SSO / SAML
  • Custom SLA (99.99%)
  • On-call engineering support
Pay As You Go
Need more? Usage beyond plan limits is billed transparently.
Sandbox compute
$0.005 / min
Per sandbox, billed by the second
Browser API
$0.002 / req
Includes proxies on paid plans
Search API
$0.003 / req
Web search + content extraction
Storage
$0.10 / GB·mo
Persistent volumes, billed daily
Bandwidth
$0.05 / GB
Outbound data transfer
No credit card for free tierPer-user tracking built inCancel anytimePay-as-you-go available
Built-in User Management

We manage your users. You build the product.

Every namespace automatically tracks per-user usage, enforces limits, and calculates costs. No billing system to build. No user management layer to maintain.

Auto User Tracking

Every API call is automatically attributed to the right user. No instrumentation needed — just pass a user ID.

Credit-Based Billing

Every resource maps to credits — compute, browser, search, storage. Set limits per user, charge what you want.

Per-User Limits

Set sandbox hours, concurrent sandboxes, API rate limits — all per user. Enforce automatically at the platform level.

Works With Any Auth

Bring your own auth. Pass any user identifier — our namespace system handles isolation, tracking, and billing from there.

How it works
01
Your user signs up
You create a namespace with any user ID from your auth system
02
Usage is tracked automatically
Every sandbox, API call, and byte of storage mapped to that user
03
Credits are consumed
Compute, browser, search, storage — all metered in credits per user
04
Limits enforced in real-time
Hit the limit? User is paused. Upgrade? Instantly unlocked
namespace.js
const ns = await oblien.namespace.create({
  userId: "user_abc123",
  limits: {
    sandboxHours: 10,
    credits: 500
  }
});

// All usage auto-tracked
const sandbox = await ns.sandbox.create();
// → credits deducted automatically
// → limits enforced in real-time
$0

Start with free credits

Every account starts with free credits — enough to prototype, test, and ship your first agent. No credit card required. When you're ready to scale, credits refill automatically based on your plan.

500free credits
~5 hours of compute

Ready to build real agents?

Sandboxes, execution, tools, and deployment. Everything your agents need to go from prototype to production.

SOC 2 ready
Free tier included
Sub-second sandbox boot
99.9% uptime SLA

Stay ahead of the agent infrastructure curve

Get updates on new primitives, sandbox features, and best practices for building production-grade AI agents.

No spam. Unsubscribe at any time.