Python SDK for AI agent tracing

mirrorkit is a lightweight, drop-in production trace collector for LLM agents. Add two lines to your existing LangChain / LangGraph / Anthropic / OpenAI script and your agent’s traces start streaming to Mirrors: non-blocking, background-batched, with negligible latency.

How do I install the Python collector?

Run pip install mirrorkit. There are no required runtime dependencies: the sender uses only the Python stdlib, so it adds nothing to your dependency tree.

pip install mirrorkit

LangChain / Anthropic / OpenAI are instrumented only if they’re importable.

How do I start collecting traces from a Python agent?

Import mirrorkit and call init() with your workspace key and a project name before your agent runs. That is the whole integration: two lines, no decorators, no changes to how you call your model.

import mirrorkit
mirrorkit.init(api_key="mk_live_...", project="my-agent")

Run your agent normally: traces are captured and shipped in the background. The endpoint defaults to the MIRROR_ENDPOINT environment variable, then to the production URL.

Options

mirrorkit.init(
    api_key="mk_live_...",
    project="my-agent",
    endpoint="https://api.runmirrors.com",  # optional override
    flush_interval=2.0,                      # seconds between batch flushes
    max_batch=50,                            # max traces per POST
    instrument=True,                         # auto-hook LangChain/Anthropic/OpenAI
)

How do I log a trace manually?

Call mirrorkit.log_trace() with a list of OpenAI-style chat dicts. This is the path for frameworks that aren’t auto-instrumented:

import mirrorkit
mirrorkit.init(api_key="mk_live_...", project="my-agent")

mirrorkit.log_trace(
    [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What's the weather in Paris?"},
        {
            "role": "assistant",
            "content": None,
            "tool_calls": [
                {
                    "id": "call_1",
                    "function": {"name": "get_weather", "arguments": '{"city": "Paris"}'},
                }
            ],
        },
        {"role": "tool", "tool_call_id": "call_1", "content": "18C, sunny"},
        {"role": "assistant", "content": "It's 18C and sunny in Paris."},
    ],
    trace_id="optional-id",
    model="gpt-4o",
)

mirrorkit.flush()  # also runs automatically at interpreter exit

Do I need to pass LangChain callbacks myself?

Normally no. init() registers a global LangChain callback handler automatically, so you don’t need to pass callbacks. If your setup doesn’t honor the global hook, pass the handler explicitly:

from langchain_core.runnables import RunnableConfig
import mirrorkit

mirrorkit.init(api_key="mk_live_...", project="my-agent")
chain.invoke(inputs, config=RunnableConfig(callbacks=[mirrorkit.handler()]))

API

Function	Description
`mirrorkit.init(api_key, project="default", endpoint=None, *, flush_interval=2.0, max_batch=50, instrument=True)`	Start the collector.
`mirrorkit.log_trace(messages, *, trace_id=None, model=None)`	Manually enqueue one trace.
`mirrorkit.flush(timeout=5.0)`	Block until the queue drains.
`mirrorkit.shutdown()`	Stop the collector.
`mirrorkit.handler()`	LangChain callback handler for manual registration.

Failures (non-2xx / network errors) are retried a couple of times, then dropped. The collector never raises into your program. The wire format is documented in the collect API reference.

The same package also ships the mirrors CLI. Install it with pip install "mirrorkit[cli]".

Get started

Collect traces

Drive Mirrors

Account

Resources

Python SDK for AI agent tracing

How do I install the Python collector?

How do I start collecting traces from a Python agent?

Options

How do I log a trace manually?

Do I need to pass LangChain callbacks myself?

API

​How do I install the Python collector?

​How do I start collecting traces from a Python agent?

​Options

​How do I log a trace manually?

​Do I need to pass LangChain callbacks myself?

​API

How do I install the Python collector?

How do I start collecting traces from a Python agent?

Options

How do I log a trace manually?

Do I need to pass LangChain callbacks myself?

API