Catalog PyPI
PACKAGE EXPLORERView in registry

agentmetrics-anthropic

PyPI

AgentMetrics observability integration for Claude Managed Agents

agentmetricsai-agentsanthropicclaudemanaged-agentsobservability
Versions collected1
Direct dependencies3From release 0.2.0
Last observed20 Oct, 22:43 UTC

README

Version 0.2.0 documentation

agentmetrics-anthropic

PyPI License: MIT

AgentMetrics integration for Claude Managed Agents (Python). Wrap your session event stream with one tracker and every session reports back to your dashboard when it terminates showing latency, cost, token counts with cache, tool calls, and errors.


Install

pip install agentmetrics-anthropic

Quickstart

import anthropic
from agentmetrics_anthropic import AgentMetricsSessionTracker

client  = anthropic.Anthropic()
tracker = AgentMetricsSessionTracker(
    agent_id="my-claude-agent",
    base_url="http://localhost:8099",
)

# Sync stream
with tracker.stream(client, session_id="sess_...") as stream:
    for event in stream:
        pass  # handle events as normal

tracker.flush()

Async

async with tracker.astream(client, session_id="sess_...") as stream:
    async for event in stream:
        pass

await tracker.flush()

API

AgentMetricsSessionTracker(agent_id, base_url)

ParameterDefaultDescription
agent_id"anthropic-agent"Label shown in the dashboard
base_url"http://localhost:8099"AgentMetrics server address

.stream(client, session_id, **kwargs)

Returns a sync context manager. Yields the same events as client.beta.sessions.events.stream(). Emits a run summary on session.status_terminated.

.astream(client, session_id, **kwargs)

Async version of .stream().

.flush(timeout=10.0)

Blocks until all in-flight HTTP requests complete. Call before process exit.


What gets tracked

Each session emits one event to /v1/events when it terminates:

FieldDescription
statussuccess or failed
duration_msWall-clock session duration
input_tokens / output_tokensAggregated across all LLM calls
cache_read_tokens / cache_write_tokensCache token counts
llm_callsNumber of LLM requests in the session
tool_calls / tool_errorsTool usage counts
tool_namesSet of tools invoked
modelModel name from the first LLM call
estimated_cost_usdComputed from token counts and model pricing
errorFirst 500 chars of the error message on failure

License

MIT

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases
VersionPublishedDirect dependenciesOpen version
0.2.020 Jun 20263

Package advisories

0
No matching advisories collected

This describes our collected data; it is not a security assessment.

Repository

PENDING
andalabx/agentmetrics

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 22:43 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:695e02d9798b4d7dc2ac5c524dacf063ceed256e95b5ef644cee0e37cbf87abb