ACS SDK for Python
Official Python SDK for AgentCloudService - Cloud hosting for autonomous AI agents.
Installation
pip install acs-sdk
Quick Start
from acs_sdk import ACS
# Register a new agent (no auth required)
result = ACS.register(name="my-research-agent")
print(f"API Key: {result.api_key}")
# Create client with API key
client = ACS(api_key=result.api_key)
# Deploy an OpenClaw agent
agent = client.deploy(
name="research-agent",
type="openclaw",
config={
"model": "claude-sonnet-4",
"channels": ["telegram", "discord"],
"skills": ["web_search", "coding"]
},
region="us-east-1"
)
print(f"Agent deployed: {agent.url}")
Features
- No CAPTCHA, No Phone Verification - Just API keys and code
- OpenClaw Native - Deploy pre-configured AI agents with channels and skills
- Multiple Deployment Types - OpenClaw, Docker, or serverless functions
- Programmatic Billing - Stripe API or USDC via x402 protocol
- Multi-Region - US, EU, and Asia-Pacific regions
Authentication
from acs_sdk import ACS
# Option 1: Pass API key directly
client = ACS(api_key="acs_live_xxx")
# Option 2: Use environment variable
# export ACS_API_KEY=acs_live_xxx
client = ACS()
API Reference
Registration (No Auth Required)
# Register new agent
result = ACS.register(
name="my-agent",
email="agent@example.com", # Optional
wallet="0x..." # Optional, for USDC payments
)
print(result.agent_id)
print(result.api_key)
# Check service status
status = ACS.status()
print(status)
Agent Management
client = ACS(api_key="acs_live_xxx")
# List all agents
agents = client.list_agents()
for agent in agents:
print(f"{agent.name}: {agent.status}")
# List running agents only
running = client.list_agents(status="running")
# Get specific agent
agent = client.get_agent("agent_xxx")
# Start/stop agent
client.start_agent("agent_xxx")
client.stop_agent("agent_xxx")
# Delete agent
client.delete_agent("agent_xxx")
Deployment
# Deploy OpenClaw agent
agent = client.deploy(
name="my-agent",
type="openclaw",
config={
"model": "claude-sonnet-4",
"channels": ["telegram", "discord", "slack"],
"skills": ["web_search", "coding", "browser"],
"memory": True
},
region="us-east-1"
)
# Deploy Docker container
agent = client.deploy(
name="custom-agent",
type="docker",
config={
"image": "my-org/my-agent:latest",
"env": {"API_KEY": "xxx"}
}
)
# Deploy serverless function
agent = client.deploy(
name="webhook-handler",
type="function",
config={
"runtime": "python3.11",
"handler": "main.handler"
}
)
Usage & Billing
# Get usage metrics
usage = client.get_usage()
print(f"Requests (24h): {usage.requests_24h}")
print(f"Compute used: {usage.compute_used} GB")
print(f"Current bill: ${usage.current_bill}")
# Get billing info
billing = client.get_billing()
# Create checkout session
checkout = client.checkout(plan="micro")
print(f"Checkout URL: {checkout['checkoutUrl']}")
# Pay with USDC
payment = client.pay_usdc(amount="19.00")
Regions
| Region | Location |
|---|---|
us-east-1 |
US East (Virginia) |
us-west-2 |
US West (Oregon) |
eu-west-1 |
EU West (Ireland) |
eu-central-1 |
EU Central (Frankfurt) |
ap-southeast-1 |
Asia Pacific (Singapore) |
ap-southeast-2 |
Asia Pacific (Sydney) |
Error Handling
from acs_sdk import ACS, ACSError, AuthenticationError, ValidationError
try:
client = ACS(api_key="invalid")
agents = client.list_agents()
except AuthenticationError:
print("Invalid API key")
except ValidationError as e:
print(f"Validation failed: {e.message}")
except ACSError as e:
print(f"API error: {e.message} (status: {e.status_code})")
Links
License
MIT License - Copyright (c) 2026 VibeCaaS / NeuralQuantum.ai LLC
Metadata
Release files for agentcloudservice 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentcloudservice-1.0.0.tar.gz | 8.1 kB | Without provenance | Details for agentcloudservice-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentcloudservice-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for agentcloudservice-1.0.0-py3-none-any.whl |
Total release size: 16.5 kB
Release files / agentcloudservice-1.0.0.tar.gz
| Download URL | agentcloudservice-1.0.0.tar.gz |
|---|---|
| Size | 8.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2cb4ab871420d788b969a5fc82ef2d6c794dc544527b709ef30de7a72b2847d8
|
|
BLAKE2b-256 checksum How to use checksums |
de61101cd4ef4090828783928a65919b0420875a71377c54b5288f248123c271
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.1
|
Release files / agentcloudservice-1.0.0-py3-none-any.whl
| Download URL | agentcloudservice-1.0.0-py3-none-any.whl |
|---|---|
| Size | 8.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
13063373bd5e8d8655fd32109d99fe7787a1890783a6bd97b9cbaa80856fa482
|
|
BLAKE2b-256 checksum How to use checksums |
d31ecf524a3f281a0a48a9d8fd96f4f67ab0ae0a4cf49bde028f36b894043a92
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.1
|
Security for agentcloudservice 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.