agentmetrics 0.1.1

Real-time cost visibility & optimization for AI agents.

AgentMetrics Python SDK

Real-time cost, latency, and error tracking for AI agents. One decorator. Zero overhead on failure.

from agentmetrics import sentinel

sentinel.configure(api_key="am_xxxxxxxxxxxxxxxx")

@sentinel.track(agent_id="customer_support")
def my_agent(task: str) -> str:
    return call_llm(task)

Every call is now tracked — duration, status, errors — visible in your AgentMetrics dashboard.

---

Prerequisites

You need a running AgentMetrics instance:

• Self-hosted (free): deploy in 60 seconds, then sign up at http://localhost/signup
• Cloud: sign up at agentmetrics.dev

After setup, get your SDK key from the dashboard: Settings → SDK Keys

---

Install

pip install agentmetrics

---

Quick start

import os
from agentmetrics import sentinel

# Configure once at startup
sentinel.configure(api_key=os.environ["AGENTMETRICS_KEY"])

@sentinel.track(agent_id="customer_support")
def handle_ticket(ticket: str) -> str:
    response = openai_client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": ticket}],
    )
    return response.choices[0].message.content

---

Framework examples

OpenAI

import os
from openai import OpenAI
from agentmetrics import sentinel

sentinel.configure(api_key=os.environ["AGENTMETRICS_KEY"])
client = OpenAI()

@sentinel.track(agent_id="openai_agent")
def ask(prompt: str) -> str:
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}],
    )
    return response.choices[0].message.content

Anthropic

import os
from anthropic import Anthropic
from agentmetrics import sentinel

sentinel.configure(api_key=os.environ["AGENTMETRICS_KEY"])
client = Anthropic()

@sentinel.track(agent_id="claude_agent")
def ask(prompt: str) -> str:
    message = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
        messages=[{"role": "user", "content": prompt}],
    )
    return message.content[0].text

LangChain

import os
from langchain_openai import ChatOpenAI
from agentmetrics import sentinel

sentinel.configure(api_key=os.environ["AGENTMETRICS_KEY"])

@sentinel.track(agent_id="langchain_agent")
def run_chain(question: str) -> str:
    llm = ChatOpenAI(model="gpt-4o-mini")
    return llm.invoke(question).content

LangGraph

import os
from agentmetrics import sentinel

sentinel.configure(api_key=os.environ["AGENTMETRICS_KEY"])

@sentinel.track(agent_id="langgraph_workflow")
def run_graph(state: dict) -> dict:
    return compiled_graph.invoke(state)

CrewAI

import os
from agentmetrics import sentinel

sentinel.configure(api_key=os.environ["AGENTMETRICS_KEY"])

@sentinel.track(agent_id="research_crew")
def run_crew(topic: str) -> str:
    return crew.kickoff(inputs={"topic": topic})

Async agents

@sentinel.track(agent_id="async_agent")
async def my_async_agent(task: str) -> str:
    result = await some_llm_call(task)
    return result

Sync and async work identically. No extra configuration needed.

---

Configuration

sentinel.configure(
    api_key="am_xxxxxxxxxxxxxxxx",        # from Settings → SDK Keys
    base_url="http://localhost:8000/v1",   # omit for cloud, set for self-hosted
)

Parameter	Default	Description
api_key	required	Your SDK key from the dashboard
base_url	https://api.agentmetrics.dev/v1	AgentMetrics API endpoint

Tip: Load from environment:

sentinel.configure(api_key=os.environ["AGENTMETRICS_KEY"])

---

Graceful degradation

If the AgentMetrics server is unreachable or the key is invalid, your agent keeps running normally. The SDK never raises exceptions, never blocks execution, and never adds latency to the critical path.

Events are sent fire-and-forget in a background thread with up to 3 retries.

---

Flushing before exit

In short-lived scripts or serverless functions, call flush() before the process exits to ensure all queued events are sent:

sentinel.flush()  # waits up to 10 seconds

---

Self-hosted

sentinel.configure(
    api_key=os.environ["AGENTMETRICS_KEY"],
    base_url="http://your-server:8000/v1",
)

---

License

Apache 2.0