freesolo 0.1.3

OpenAI and Anthropic tracing package for LLM applications.

freesolo

freesolo is a Python tracing package for LLM apps.

It is built for the lowest-friction integration possible:

1. Install the package
2. Set FREESOLO_API_KEY
3. Wrap your OpenAI or Anthropic client
4. Call the client normally

Current provider support

freesolo currently supports automatic client instrumentation for:

• OpenAI
• Anthropic

Install

Install the package plus the provider SDK you use:

pip install freesolo openai

or

pip install freesolo anthropic

Environment

• FREESOLO_API_KEY

Quickstart

from openai import OpenAI
from freesolo import instrument_openai

client = instrument_openai(OpenAI())

result = client.chat.completions.create(
    model="gpt-4.1-mini",
    messages=[
        {"role": "user", "content": "How do I reset my password?"},
    ],
)

print(result.choices[0].message.content or "")

Group Multiple Model Calls

For agentic or long-horizon tasks, strongly prefer wrapping the whole task in start_trace(...) so all of the model calls land in one trace.

For a single one-off OpenAI or Anthropic request, you can skip it.

from anthropic import Anthropic
from freesolo import instrument_anthropic, start_trace

client = instrument_anthropic(Anthropic())

with start_trace("support-agent-run"):
    first = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=64,
        messages=[{"role": "user", "content": "Say hello"}],
    )
    second = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=64,
        messages=[{"role": "user", "content": "Say goodbye"}],
    )

What Gets Stored

• Trace metadata if you explicitly pass it to start_trace(..., metadata=...)
• OpenAI and Anthropic request + response payloads
• Token usage when available
• Image inputs with inline previews for the trace UI

Notes

• You do not need @trace() for ordinary LLM tracing.
• A single instrumented OpenAI or Anthropic request creates a trace automatically.
• For agentic or long-horizon workflows, strongly recommend start_trace(trace_id=...) so planning, retries, and follow-up calls stay grouped.
• Delivery is best-effort by default. Trace ingestion failures do not break your app.