Developers

AI agent monitoring and uptime tracking with two lines of code. Python, Node.js, CLI, LangChain, CrewAI, AutoGen. Pick your flavor. Everything ships with your stack.

SDKs & CLI

2 lines to start monitoring.

Register your agent and it's being validated from real devices worldwide within seconds. No configuration, no infrastructure, no code changes to your agent.

pippip install agent-status-sdk
npmnpm install @agentstatus/sdk
npxnpx @agentstatus/cli
Live
# pip install agentstatus
import agentstatus

# Initialize with your API key
agentstatus.init(api_key="as_xxx")

# Register your agent. Now monitored 24/7 from real devices worldwide
agentstatus.register(
    endpoint="https://api.mycompany.com/chat",
    name="Customer Support Bot",
    auth={"type": "bearer", "token": "..."},
)

# Check status anytime
status = agentstatus.status(agent_id="abc-123")
print(status.latency, status.gold_passing)  # 234ms, 3/3

# One-off validation run
result = agentstatus.run(
    endpoint="https://api.mycompany.com/chat",
    prompts=["What is 2+2?", "Return JSON: {x:1}"]
)
github.com/Carmel-Labs-Inc/agentstatus-sdk

Framework Integrations

Works with your stack.

LangChain, CrewAI, AutoGen, OpenAI, Anthropic. Agent Status integrates with how you already build. One line to expose any local agent to user-side monitoring.

LangChain

Callback handler or expose() for user-side monitoring of chains and agents. No deployment required.

from agentstatus.integrations.langchain import expose expose(my_chain, api_key="as_xxx", agent_name="My Chain")
Live

CrewAI

Agent Status EventListener for multi-agent crews. Track which agents in your crew are healthy and fast.

from agentstatus.integrations.crewai import StatusEventListener crew = Crew(..., listeners=[StatusEventListener( api_key="as_xxx")])
Live

AutoGen

Agent Status AgentWrapper and ConversationTracker for multi-agent conversation monitoring.

from agentstatus.integrations.autogen import StatusAgentWrapper agent = StatusAgentWrapper( base_agent, api_key="as_xxx")
Live

OpenAI

Drop-in StatusOpenAI client. Use it exactly like the official OpenAI client. Latency, errors, and usage tracked automatically.

from agentstatus.integrations.openai_wrapper import StatusOpenAI client = StatusOpenAI( api_key="as_xxx") # Use like regular OpenAI client
Live

Anthropic

Drop-in StatusAnthropic client for Claude-based agents. Identical API surface, automatic observability layer.

from agentstatus.integrations.anthropic_wrapper import StatusAnthropic client = StatusAnthropic( api_key="as_xxx")
Live

expose(): The Key Primitive

One function call. Your local agent is now reachable by Agent Status's distributed test network worldwide. No deployment. No port forwarding. No ngrok.

# Works with any framework expose(my_agent, api_key="as_xxx") # Agent Status tests from Sao Paulo, Tokyo, Lagos...
Live

Tunnel Relay

Monitor before you deploy.

Testing locally? Agent Status can still test your agent from real devices worldwide. No deployment, no port forwarding, no ngrok. Powered by agentstatus-tunnel.carmel.so.

python
from agentstatus.integrations.langchain import expose

# Your agent is running on localhost
chain = LLMChain(...)

# One line: tunnel opens to agentstatus-tunnel.carmel.so
expose(chain,
    api_key="as_xxx",
    agent_name="Dev Agent"
)

# Now Agent Status tests it from:
# Sao Paulo, Tokyo, Lagos, Frankfurt, Mumbai...
localhost:8000
Your agent
WSS persistent
as-tunnel
.carmel.so
test traffic
30 Nodes
6 regions
No deployment required
No port forwarding or firewall changes
No ngrok or third-party tunnels
SSL secured via Cloudflare Zero Trust

CLI Reference

Command-line first.

Integrate into CI/CD pipelines, run post-deploy checks, debug from your terminal. Identical feature parity between Python and Node CLIs.

agentstatus · zsh
~ $ rora status my-agent-id
✓ UP
Latency: 245ms
Gold: 3/3 passing
Last check: 2 min ago
~ $ rora run my-agent-id
Running validation from 5 nodes...
├── US-West 212ms
├── EU-Central 445ms
├── APAC 534ms
├── SA 612ms
└── ME 490ms
✓ All checks passed (5/5)
~ $ rora list
ID NAME STATUS LATENCY
abc-123 Customer Support Bot UP 245ms
def-456 Research Agent UP 388ms
ghi-789 Coding Assistant WARN 1240ms
CommandDescription
agentstatus registerRegister a new agent for monitoring
agentstatus listList all monitored agents and their status
agentstatus status <id>Get current health, latency, and gold prompt results
agentstatus run <id>Trigger a manual validation run from 5 nodes
agentstatus delete <id>Remove an agent from monitoring
pippip install rora → rora command
npmnpm install -g @rora-ai/rora

MCP Server

AI-native from day one.

Agent Status speaks MCP. Add agent monitoring capabilities to Claude Desktop, Cursor, or any MCP-compatible AI assistant. Ask in plain English.

MCP
You

Hey Claude, is my production agent healthy right now?

Claude

Let me check that for you.

agent_status({ agent_id: "abc-123" })

Your agent is UP. Latency: 234ms. Eval checks: 3/3 passing. Last check: 47 seconds ago.

You

Run a full validation and tell me if anything fails.

Claude

Running validation across all nodes now.

agentstatus_run({ agent_id: "abc-123" })

All 5 nodes passed. No failures. P95 latency: 445ms.

agentstatus_register
Register agent
agentstatus_status
Get status
agentstatus_run
Trigger run
agentstatus_list
List agents
agentstatus_delete
Remove agent

Setup in 60 seconds

Start the MCP server, drop the config into Claude Desktop or Cursor, and Agent Status tools appear instantly.

mcp_config.json
{
  "servers": {
    "agentstatus": {
      "command": "python",
      "args": ["-m", "agentstatus.mcp"],
      "env": {
        "AGENTSTATUS_API_KEY": "as_xxx"
      }
    }
  }
}
python -m agentstatus.mcp

Compatible with

Claude DesktopCursorAny MCP Client

Open Source

Integration layer is open source.

Fork it, extend it, contribute back. The SDKs, CLIs, integrations, and MCP server are all public under the Carmel Labs GitHub org.

What's open source

Python SDK + CLI
Node.js SDK + CLI
Framework integrations (LangChain, CrewAI, AutoGen)
Drop-in wrappers (OpenAI, Anthropic)
MCP server implementation
OpenAPI spec

Private infrastructure

Distributed node network
LLM judge + scoring engine
Tunnel relay infrastructure
Billing, admin, discovery engine

Get started today

Your agent is running.
Is it working?

Two lines of code to find out. Free forever for 3 checks per day.