All Systems Operational

Where AI AgentsLive & Operate

Your agent gets its own runtime — persistent or ephemeral.It can live there around the clock, or spin one up for asingle task. One SDK to control everything.

Built for
AutoGPT
CrewAI
LangChain
MetaGPT
BabyAGI
OpenClaw
oblien — terminal
zsh
Latency190ms
Regionus-east
oblien sdk v2.0
<200ms
Boot time
2.4M+
Tasks run
99.9%
Uptime
Scroll to explore
Two Modes

Give your agent a home.Or hand it a task.

Persistent for agents that live and operate around the clock. Ephemeral for agents that spin up, complete a task, and move on.

Persistent sandbox

Your agent’spermanent home

Your agent moves in and operates 24/7. Full isolation, root access, real networking. It owns the environment — custom domains, SSL, and monitoring are all built in.

Agent stays running — survives restarts
Full root access with real isolated networking
Custom domains, SSL, monitoring built in
Any framework — LangChain, CrewAI, AutoGPT
Short-lived sandbox

On-demand workspacefor any task

Spin up sandboxes on demand — your agent executes code, reads and writes files, runs tests. When it's done, the sandbox disappears. Controlled through SDK or MCP.

Agent spins up, executes, shuts down
SDK & MCP for full programmatic control
File ops, shell, networking — all via code
Granular resource limits per workspace

Same platform. Same SDK. You choose how your agent runs.

Everything your agent needs to operate

Execution, storage, deployment, and tools — the building blocks of autonomous agents.

Network

Complete networking stack with exposed ports and firewall rules. Agents communicate, serve, and connect.

Isolation

Every sandbox is isolated. Process, network, and filesystem separation per agent and tenant.

Streaming

WebSocket connections stream output in real-time. Watch agents execute live.

SSH Access

Full root SSH into running sandboxes. Debug, inspect, or take manual control.

Browser

tool

Agents navigate sites, fill forms, extract data, and capture screenshots with headless Chrome.

Search

tool

Agents search the web and extract content — pages, PDFs, structured data.

Execution

Your agent installs packages, runs services, and manages processes with full system access. Python, Node.js, Bash, Go — any runtime, real-time streaming.

Environment

Your agent reads, writes, and organizes files with persistent volumes across sessions — nothing is lost between runs.

Deployment

Your agent ships what it builds. One call turns any sandbox into a live URL with custom domains, auto SSL, and edge routing.

Agent Tooling

Your agent does more than run code.It searches, patches, and snapshots.

Semantic search. Batch file patching. Environment snapshots. Operations that would take days to build with shell scripts— exposed as MCP resources and tool definitions your agent can call instantly.

Execute any command — shell, Python, Node, Go. Stream stdout in real-time.

result = await sandbox.exec("python train.py")

Code it or click it. Every feature is available as MCP resources, tool definitions, or SDK calls for your agent— and through a fully managed dashboard when you need manual control. Same power, your choice.

No SSH, no bash scripts. Semantic search, diff patching, snapshot rollback — capabilities you'd spend days building with shell commands. Here, they're one tool call away.

.exec.files.patch.files.search.snapshot.publish.grepSDKCLIENT
Files
Shell
Git
Snapshots
WebSocket
Ports
Databases
GPU
What You Can Build

Agents that actually operate

From personal assistants to production platforms — agents that actually get things done.

Personal Agent

Run any agent framework on isolated sandboxes

Run any open-source agent like OpenClaw, AutoGPT, or your own — each gets a secure, isolated cloud sandbox with full power. Persistent memory, unrestricted networking, and real compute. Your agent runs 24/7 without draining local resources.

16GB
Memory
Optional
GPUs
APIs
Works with
OpenClaw
AutoGPT
LangChain
CrewAI
Run any open-source agent
Sandboxes remain active indefinitely
Complete sandbox isolation
oblien — personal
Persistent
CPU2.3 vCPU
RAM4.2GB
NET↑42MB/s
oblien sdk v2.0
Every sandbox includes
Full 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.

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.

Same platform. Code or dashboard. Your choice.

Stop Duct-Taping Agent Infrastructure

Security is hard. Isolation is hard. Multi-tenant billing is hard. Per-user tracking is hard. Everything’s built in — so you ship agents, not plumbing.

DIY Approach~27 weeks
Container orchestration
~6 wks
Security & escape prevention
~5 wks
Multi-tenant isolation
~4 wks
Per-user billing & tracking
~5 wks
Tool integrations
~4 wks
Deployment pipeline
~3 wks
vs
Oblien~5 min
Isolated sandboxes via API
.create()
Security built in
.config
Multi-tenant by default
.namespace
Per-user billing included
.credits
All tools as primitives
.tools.*
Ship with one call
.publish()
27 weeksof engineering saved
1 importto replace it all
$0to start building
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
Multi-Agent Platforms

Give every user their own agent. At any scale.

Namespaces, credit metering, quota enforcement, and billing primitives — all built in. Ship a multi-tenant product without building the infrastructure layer yourself.

Namespace Isolation

Every tenant gets a namespace. Sandboxes, usage, and billing are scoped and isolated automatically — no cross-contamination.

Credit-Based Metering

Compute, storage, tools — everything maps to credits. Accurate down to the second. Set prices, margins, and thresholds your way.

Quota Enforcement

Sandbox hours, concurrent instances, API rate limits — all enforced at the platform level. Hit the limit, paused instantly.

Any Auth, Any Stack

Bring your own auth. Pass any identifier — our namespace layer handles isolation, metering, and billing from there.

How it works
01
Create a namespace
Scope everything — sandboxes, credits, limits — to a single tenant or project
02
Usage is metered automatically
Every sandbox, API call, and byte of storage tracked in real-time credits
03
Quotas enforced at the edge
Concurrency limits, rate caps, credit ceilings — all enforced before execution
04
Bill with precision
Export usage or let our billing primitives handle it. Accurate to the millisecond
billing.js
const ns = await oblien.namespace.create({
  tenantId: "org_acme",
  plan: "pro",
  limits: {
    sandboxHours: 100,
    concurrency: 5,
    credits: 5000
  }
});

// All usage auto-metered
const sb = await ns.sandbox.create();
// → credits deducted per second
// → quotas enforced at the edge
$0

Start with free credits

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

500free credits
~5 hours of compute

Your agents are ready to operate.

A home to live in. A workspace to operate from. One platform. Start free, scale to production.

No credit card required
Free tier included
Production-grade infra
99.9% uptime SLA

The future of AI agents is autonomous

Get updates on new agent capabilities, platform features, and best practices for building production-grade AI agents.

No spam. Unsubscribe at any time.